From ca2edd97ed6542a643402db0d58e7040135fd56f Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 11 五月 2023 16:21:25 +0800
Subject: [PATCH] Merge pull request #494 from alibaba-damo-academy/dev_lyh
---
docs/m2met2/_build/html/Track_setting_and_evaluation.html | 8
docs/m2met2_cn/_build/html/search.html | 8
docs/m2met2_cn/_build/doctrees/联系方式.doctree | 0
docs/m2met2_cn/基线.md | 27 ++
egs/alimeeting/sa-asr/asr_local.sh | 143 ++---------
docs/m2met2/_build/html/_sources/Organizers.md.txt | 2
docs/m2met2_cn/index.rst | 4
docs/m2met2_cn/联系方式.md | 6
docs/m2met2/Organizers.md | 2
docs/m2met2_cn/_build/doctrees/index.doctree | 0
docs/m2met2/_build/html/Contact.html | 15
docs/m2met2_cn/_build/html/_images/baseline_result.png | 0
docs/m2met2_cn/_build/doctrees/environment.pickle | 0
docs/m2met2_cn/_build/html/联系方式.html | 17
docs/m2met2_cn/_build/html/_sources/简介.md.txt | 29 +-
docs/m2met2/_build/html/_sources/Introduction.md.txt | 20
docs/m2met2/_build/doctrees/environment.pickle | 0
docs/m2met2/_build/html/index.html | 8
docs/m2met2_cn/_build/html/genindex.html | 8
docs/m2met2/_build/doctrees/Contact.doctree | 0
docs/m2met2/_build/html/_sources/Baseline.md.txt | 27 ++
README.md | 4
docs/m2met2/Contact.md | 4
docs/m2met2/images/qrcode.png | 0
docs/m2met2_cn/_build/html/简介.html | 36 +-
docs/m2met2/_build/html/Baseline.html | 35 ++
docs/m2met2/_build/html/objects.inv | 2
egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py | 7
docs/m2met2_cn/_build/html/基线.html | 35 ++
docs/m2met2_cn/_build/html/_sources/基线.md.txt | 27 ++
docs/m2met2/_build/html/Dataset.html | 8
docs/m2met2/_build/html/_sources/Contact.md.txt | 4
docs/m2met2_cn/_build/html/_sources/赛道设置与评估.md.txt | 2
docs/m2met2/_build/html/_images/qrcode.png | 0
docs/m2met2_cn/_build/html/index.html | 12
docs/m2met2_cn/_build/html/组委会.html | 8
docs/m2met2_cn/_build/doctrees/简介.doctree | 0
docs/m2met2_cn/images/baseline_result.png | 0
docs/m2met2/_build/html/search.html | 8
docs/m2met2/_build/html/Rules.html | 8
egs/alimeeting/sa-asr/README.md | 6
docs/m2met2/conf.py | 2
docs/m2met2_cn/_build/html/_sources/联系方式.md.txt | 6
egs/alimeeting/sa-asr/run.sh | 8
docs/m2met2_cn/_build/html/.buildinfo | 2
docs/m2met2/Baseline.md | 27 ++
docs/m2met2_cn/images/qrcode.png | 0
docs/m2met2/_build/doctrees/Baseline.doctree | 0
docs/m2met2/_build/doctrees/Organizers.doctree | 0
docs/m2met2_cn/简介.md | 29 +-
docs/m2met2/_build/html/searchindex.js | 2
docs/m2met2_cn/_build/html/赛道设置与评估.html | 10
docs/m2met2_cn/_build/doctrees/基线.doctree | 0
docs/m2met2_cn/_build/html/规则.html | 8
docs/m2met2/_build/html/.buildinfo | 2
docs/m2met2/_build/html/Introduction.html | 28 +-
docs/m2met2_cn/_build/html/数据集.html | 8
docs/m2met2_cn/conf.py | 2
docs/m2met2_cn/_build/doctrees/赛道设置与评估.doctree | 0
docs/m2met2/_build/html/_images/baseline_result.png | 0
docs/m2met2/_build/html/genindex.html | 8
docs/m2met2_cn/_build/html/searchindex.js | 2
docs/m2met2_cn/_build/html/objects.inv | 0
docs/m2met2_cn/_build/html/_images/qrcode.png | 0
docs/m2met2/images/baseline_result.png | 0
docs/m2met2/_build/html/Organizers.html | 10
docs/m2met2_cn/_build/html/_sources/index.rst.txt | 4
docs/m2met2/Introduction.md | 20
docs/m2met2_cn/赛道设置与评估.md | 2
docs/m2met2/_build/doctrees/Introduction.doctree | 0
70 files changed, 382 insertions(+), 328 deletions(-)
diff --git a/README.md b/README.md
index 64d6d89..e9c6ef9 100644
--- a/README.md
+++ b/README.md
@@ -21,8 +21,8 @@
| [**M2MET2.0 Challenge**](https://github.com/alibaba-damo-academy/FunASR#multi-channel-multi-party-meeting-transcription-20-m2met20-challenge)
## What's new:
-### Multi-Channel Multi-Party Meeting Transcription 2.0 (M2MET2.0) Challenge
-We are pleased to announce that the M2MeT2.0 challenge will be held in the near future. The baseline system is conducted on FunASR and is provided as a receipe of AliMeeting corpus. For more details you can see the guidence of M2MET2.0 ([CN](https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/index.html)/[EN](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)).
+### Multi-Channel Multi-Party Meeting Transcription 2.0 (M2MeT2.0) Challenge
+We are pleased to announce that the M2MeT2.0 challenge has been accepted by the ASRU 2023 challenge special session. The registration is now open. The baseline system is conducted on FunASR and is provided as a receipe of AliMeeting corpus. For more details you can see the guidence of M2MET2.0 ([CN](https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/index.html)/[EN](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)).
### Release notes
For the release notes, please ref to [news](https://github.com/alibaba-damo-academy/FunASR/releases)
diff --git a/docs/m2met2/Baseline.md b/docs/m2met2/Baseline.md
index 6f9609b..4e12162 100644
--- a/docs/m2met2/Baseline.md
+++ b/docs/m2met2/Baseline.md
@@ -1,13 +1,34 @@
# Baseline
## Overview
-We will release an E2E SA-ASR~\cite{kanda21b_interspeech} baseline conducted on [FunASR](https://github.com/alibaba-damo-academy/FunASR) at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.
+We will release an E2E SA-ASR baseline conducted on [FunASR](https://github.com/alibaba-damo-academy/FunASR) at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.
## Quick start
-#TODO: fill with the README.md of the baseline
+To run the baseline, first you need to install FunASR and ModelScope. ([installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html))
+There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.
+Before running `run.sh`, you must manually download and unpack the [AliMeeting](http://www.openslr.org/119/) corpus and place it in the `./dataset` directory:
+```shell
+dataset
+|鈥斺�� Eval_Ali_far
+|鈥斺�� Eval_Ali_near
+|鈥斺�� Test_Ali_far
+|鈥斺�� Test_Ali_near
+|鈥斺�� Train_Ali_far
+|鈥斺�� Train_Ali_near
+```
+Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
+```shell
+data/Test_2023_Ali_far
+|鈥斺�� wav.scp
+|鈥斺�� wav_raw.scp
+|鈥斺�� segments
+|鈥斺�� utt2spk
+|鈥斺�� spk2utt
+```
+For more details you can see [here](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## Baseline results
The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/m2met2/Contact.md b/docs/m2met2/Contact.md
index 3097ad7..6aa3bb7 100644
--- a/docs/m2met2/Contact.md
+++ b/docs/m2met2/Contact.md
@@ -1,9 +1,9 @@
# Contact
-If you have any questions about M2MET2.0 challenge, please contact us by
+If you have any questions about M2MeT2.0 challenge, please contact us by
- email: [m2met.alimeeting@gmail.com](mailto:m2met.alimeeting@gmail.com)
| Wechat group |
|:------------------------------------------:|
-<!-- | <img src="images/wechat.png" width="300"/> | -->
+| <img src="images/qrcode.png" width="300"/> |
diff --git a/docs/m2met2/Introduction.md b/docs/m2met2/Introduction.md
index eac9eb6..fc7c356 100644
--- a/docs/m2met2/Introduction.md
+++ b/docs/m2met2/Introduction.md
@@ -6,23 +6,23 @@
The ICASSP2022 M2MeT challenge focuses on meeting scenarios, and it comprises two main tasks: speaker diarization and multi-speaker automatic speech recognition. The former involves identifying who spoke when in the meeting, while the latter aims to transcribe speech from multiple speakers simultaneously, which poses significant technical difficulties due to overlapping speech and acoustic interferences.
-Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying "who spoke what at when". To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models' performance and advance the state of the art in this area.
+Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU 2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying "who spoke what at when". To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models' performance and advance the state of the art in this area.
## Timeline(AOE Time)
- $ April~29, 2023: $ Challenge and registration open.
-- $ May~8, 2023: $ Baseline release.
-- $ May~15, 2023: $ Registration deadline, the due date for participants to join the Challenge.
-- $ June~9, 2023: $ Test data release and leaderboard open.
-- $ June~13, 2023: $ Final submission deadline.
-- $ June~19, 2023: $ Evaluation result and ranking release.
+- $ May~11, 2023: $ Baseline release.
+- $ May~22, 2023: $ Registration deadline, the due date for participants to join the Challenge.
+- $ June~16, 2023: $ Test data release and leaderboard open.
+- $ June~20, 2023: $ Final submission deadline and leaderboar close.
+- $ June~26, 2023: $ Evaluation result and ranking release.
- $ July~3, 2023: $ Deadline for paper submission.
- $ July~10, 2023: $ Deadline for final paper submission.
-- $ December~12\ to\ 16, 2023: $ ASRU Workshop and challenge session
+- $ December~12\ to\ 16, 2023: $ ASRU Workshop and Challenge Session.
## Guidelines
-Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 15, 2023.
+Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 22, 2023. Participants are also welcome to join the [wechat group](https://alibaba-damo-academy.github.io/FunASR/m2met2/Contact.html) of M2MeT2.0 and keep up to date with the latest updates about the challenge.
-[M2MET2.0 Registration](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
+[M2MeT2.0 Registration](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
-Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top three submissions to be included in the ASRU2023 Proceedings.
+Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top ranking submissions to be included in the ASRU2023 Proceedings.
diff --git a/docs/m2met2/Organizers.md b/docs/m2met2/Organizers.md
index e16c803..f5a9da2 100644
--- a/docs/m2met2/Organizers.md
+++ b/docs/m2met2/Organizers.md
@@ -1,5 +1,5 @@
# Organizers
-***Lei Xie, Professor, Northwestern Polytechnical University, China***
+***Lei Xie, Professor, AISHELL foundation, China***
Email: [lxie@nwpu.edu.cn](mailto:lxie@nwpu.edu.cn)
diff --git a/docs/m2met2/_build/doctrees/Baseline.doctree b/docs/m2met2/_build/doctrees/Baseline.doctree
index 9fc7c50..f6ea62f 100644
--- a/docs/m2met2/_build/doctrees/Baseline.doctree
+++ b/docs/m2met2/_build/doctrees/Baseline.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/Contact.doctree b/docs/m2met2/_build/doctrees/Contact.doctree
index e3f579f..0508819 100644
--- a/docs/m2met2/_build/doctrees/Contact.doctree
+++ b/docs/m2met2/_build/doctrees/Contact.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/Introduction.doctree b/docs/m2met2/_build/doctrees/Introduction.doctree
index 84f1baa..6ffceef 100644
--- a/docs/m2met2/_build/doctrees/Introduction.doctree
+++ b/docs/m2met2/_build/doctrees/Introduction.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/Organizers.doctree b/docs/m2met2/_build/doctrees/Organizers.doctree
index 0f571a3..7ecfbdf 100644
--- a/docs/m2met2/_build/doctrees/Organizers.doctree
+++ b/docs/m2met2/_build/doctrees/Organizers.doctree
Binary files differ
diff --git a/docs/m2met2/_build/doctrees/environment.pickle b/docs/m2met2/_build/doctrees/environment.pickle
index ea9c740..fe68059 100644
--- a/docs/m2met2/_build/doctrees/environment.pickle
+++ b/docs/m2met2/_build/doctrees/environment.pickle
Binary files differ
diff --git a/docs/m2met2/_build/html/.buildinfo b/docs/m2met2/_build/html/.buildinfo
index d62b4cf..97d32c4 100644
--- a/docs/m2met2/_build/html/.buildinfo
+++ b/docs/m2met2/_build/html/.buildinfo
@@ -1,4 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 9907eab6bf227ca0fc6db297f26919da
+config: a62852d90c3e533904d811bbf85f977d
tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/m2met2/_build/html/Baseline.html b/docs/m2met2/_build/html/Baseline.html
index e52d322..62c656c 100644
--- a/docs/m2met2/_build/html/Baseline.html
+++ b/docs/m2met2/_build/html/Baseline.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Baseline — m2met2 documentation</title>
+ <title>Baseline — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -44,7 +44,7 @@
<li class="right" >
<a href="Track_setting_and_evaluation.html" title="Track & Evaluation"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Baseline</a></li>
</ul>
</div>
@@ -55,7 +55,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -126,17 +126,38 @@
<h1>Baseline<a class="headerlink" href="#baseline" title="Permalink to this heading">露</a></h1>
<section id="overview">
<h2>Overview<a class="headerlink" href="#overview" title="Permalink to this heading">露</a></h2>
-<p>We will release an E2E SA-ASR~\cite{kanda21b_interspeech} baseline conducted on <a class="reference external" href="https://github.com/alibaba-damo-academy/FunASR">FunASR</a> at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.</p>
+<p>We will release an E2E SA-ASR baseline conducted on <a class="reference external" href="https://github.com/alibaba-damo-academy/FunASR">FunASR</a> at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.</p>
<p><img alt="model archietecture" src="_images/sa_asr_arch.png" /></p>
</section>
<section id="quick-start">
<h2>Quick start<a class="headerlink" href="#quick-start" title="Permalink to this heading">露</a></h2>
-<p>#TODO: fill with the README.md of the baseline</p>
+<p>To run the baseline, first you need to install FunASR and ModelScope. (<a class="reference external" href="https://alibaba-damo-academy.github.io/FunASR/en/installation.html">installation</a>)<br />
+There are two startup scripts, <code class="docutils literal notranslate"><span class="pre">run.sh</span></code> for training and evaluating on the old eval and test sets, and <code class="docutils literal notranslate"><span class="pre">run_m2met_2023_infer.sh</span></code> for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 (<a class="reference external" href="https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html">M2MeT2.0</a>) Challenge.<br />
+Before running <code class="docutils literal notranslate"><span class="pre">run.sh</span></code>, you must manually download and unpack the <a class="reference external" href="http://www.openslr.org/119/">AliMeeting</a> corpus and place it in the <code class="docutils literal notranslate"><span class="pre">./dataset</span></code> directory:</p>
+<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>dataset
+<span class="p">|</span>鈥斺��<span class="w"> </span>Eval_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Eval_Ali_near
+<span class="p">|</span>鈥斺��<span class="w"> </span>Test_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Test_Ali_near
+<span class="p">|</span>鈥斺��<span class="w"> </span>Train_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Train_Ali_near
+</pre></div>
+</div>
+<p>Before running <code class="docutils literal notranslate"><span class="pre">run_m2met_2023_infer.sh</span></code>, you need to place the new test set <code class="docutils literal notranslate"><span class="pre">Test_2023_Ali_far</span></code> (to be released after the challenge starts) in the <code class="docutils literal notranslate"><span class="pre">./dataset</span></code> directory, which contains only raw audios. Then put the given <code class="docutils literal notranslate"><span class="pre">wav.scp</span></code>, <code class="docutils literal notranslate"><span class="pre">wav_raw.scp</span></code>, <code class="docutils literal notranslate"><span class="pre">segments</span></code>, <code class="docutils literal notranslate"><span class="pre">utt2spk</span></code> and <code class="docutils literal notranslate"><span class="pre">spk2utt</span></code> in the <code class="docutils literal notranslate"><span class="pre">./data/Test_2023_Ali_far</span></code> directory.</p>
+<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>data/Test_2023_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>wav.scp
+<span class="p">|</span>鈥斺��<span class="w"> </span>wav_raw.scp
+<span class="p">|</span>鈥斺��<span class="w"> </span>segments
+<span class="p">|</span>鈥斺��<span class="w"> </span>utt2spk
+<span class="p">|</span>鈥斺��<span class="w"> </span>spk2utt
+</pre></div>
+</div>
+<p>For more details you can see <a class="reference external" href="https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md">here</a></p>
</section>
<section id="baseline-results">
<h2>Baseline results<a class="headerlink" href="#baseline-results" title="Permalink to this heading">露</a></h2>
<p>The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.</p>
-<p><img alt="baseline result" src="_images/baseline_result.png" /></p>
+<p><img alt="baseline_result" src="_images/baseline_result.png" /></p>
</section>
</section>
@@ -170,7 +191,7 @@
<li class="right" >
<a href="Track_setting_and_evaluation.html" title="Track & Evaluation"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Baseline</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Contact.html b/docs/m2met2/_build/html/Contact.html
index eafd2d5..f268ef4 100644
--- a/docs/m2met2/_build/html/Contact.html
+++ b/docs/m2met2/_build/html/Contact.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Contact — m2met2 documentation</title>
+ <title>Contact — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -40,7 +40,7 @@
<li class="right" >
<a href="Organizers.html" title="Organizers"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Contact</a></li>
</ul>
</div>
@@ -51,7 +51,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -120,7 +120,7 @@
<section id="contact">
<h1>Contact<a class="headerlink" href="#contact" title="Permalink to this heading">露</a></h1>
-<p>If you have any questions about M2MET2.0 challenge, please contact us by</p>
+<p>If you have any questions about M2MeT2.0 challenge, please contact us by</p>
<ul class="simple">
<li><p>email: <a class="reference external" href="mailto:m2met.alimeeting%40gmail.com">m2met<span>.</span>alimeeting<span>@</span>gmail<span>.</span>com</a></p></li>
</ul>
@@ -129,8 +129,11 @@
<tr class="row-odd"><th class="head text-center"><p>Wechat group</p></th>
</tr>
</thead>
+<tbody>
+<tr class="row-even"><td class="text-center"><p><a class="reference internal" href="_images/qrcode.png"><img alt="_images/qrcode.png" src="_images/qrcode.png" style="width: 300px;" /></a></p></td>
+</tr>
+</tbody>
</table>
-<!-- | <img src="images/wechat.png" width="300"/> | -->
</section>
@@ -157,7 +160,7 @@
<li class="right" >
<a href="Organizers.html" title="Organizers"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Contact</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Dataset.html b/docs/m2met2/_build/html/Dataset.html
index 43bf8a1..f6b2a04 100644
--- a/docs/m2met2/_build/html/Dataset.html
+++ b/docs/m2met2/_build/html/Dataset.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Datasets — m2met2 documentation</title>
+ <title>Datasets — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="Introduction.html" title="Introduction"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Datasets</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -181,7 +181,7 @@
<li class="right" >
<a href="Introduction.html" title="Introduction"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Datasets</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Introduction.html b/docs/m2met2/_build/html/Introduction.html
index 2ddafe2..82394fc 100644
--- a/docs/m2met2/_build/html/Introduction.html
+++ b/docs/m2met2/_build/html/Introduction.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Introduction — m2met2 documentation</title>
+ <title>Introduction — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="index.html" title="ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Introduction</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -130,27 +130,27 @@
<p>Automatic speech recognition (ASR) and speaker diarization have made significant strides in recent years, resulting in a surge of speech technology applications across various domains. However, meetings present unique challenges to speech technologies due to their complex acoustic conditions and diverse speaking styles, including overlapping speech, variable numbers of speakers, far-field signals in large conference rooms, and environmental noise and reverberation.</p>
<p>Over the years, several challenges have been organized to advance the development of meeting transcription, including the Rich Transcription evaluation and Computational Hearing in Multisource Environments (CHIME) challenges. The latest iteration of the CHIME challenge has a particular focus on distant automatic speech recognition and developing systems that can generalize across various array topologies and application scenarios. However, while progress has been made in English meeting transcription, language differences remain a significant barrier to achieving comparable results in non-English languages, such as Mandarin. The Multimodal Information Based Speech Processing (MISP) and Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenges have been instrumental in advancing Mandarin meeting transcription. The MISP challenge seeks to address the problem of audio-visual distant multi-microphone signal processing in everyday home environments, while the M2MeT challenge focuses on tackling the speech overlap issue in offline meeting rooms.</p>
<p>The ICASSP2022 M2MeT challenge focuses on meeting scenarios, and it comprises two main tasks: speaker diarization and multi-speaker automatic speech recognition. The former involves identifying who spoke when in the meeting, while the latter aims to transcribe speech from multiple speakers simultaneously, which poses significant technical difficulties due to overlapping speech and acoustic interferences.</p>
-<p>Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying 鈥渨ho spoke what at when鈥�. To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models鈥� performance and advance the state of the art in this area.</p>
+<p>Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU 2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying 鈥渨ho spoke what at when鈥�. To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models鈥� performance and advance the state of the art in this area.</p>
</section>
<section id="timeline-aoe-time">
<h2>Timeline(AOE Time)<a class="headerlink" href="#timeline-aoe-time" title="Permalink to this heading">露</a></h2>
<ul class="simple">
<li><p><span class="math notranslate nohighlight">\( April~29, 2023: \)</span> Challenge and registration open.</p></li>
-<li><p><span class="math notranslate nohighlight">\( May~8, 2023: \)</span> Baseline release.</p></li>
-<li><p><span class="math notranslate nohighlight">\( May~15, 2023: \)</span> Registration deadline, the due date for participants to join the Challenge.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~9, 2023: \)</span> Test data release and leaderboard open.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~13, 2023: \)</span> Final submission deadline.</p></li>
-<li><p><span class="math notranslate nohighlight">\( June~19, 2023: \)</span> Evaluation result and ranking release.</p></li>
+<li><p><span class="math notranslate nohighlight">\( May~11, 2023: \)</span> Baseline release.</p></li>
+<li><p><span class="math notranslate nohighlight">\( May~22, 2023: \)</span> Registration deadline, the due date for participants to join the Challenge.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~16, 2023: \)</span> Test data release and leaderboard open.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~20, 2023: \)</span> Final submission deadline and leaderboar close.</p></li>
+<li><p><span class="math notranslate nohighlight">\( June~26, 2023: \)</span> Evaluation result and ranking release.</p></li>
<li><p><span class="math notranslate nohighlight">\( July~3, 2023: \)</span> Deadline for paper submission.</p></li>
<li><p><span class="math notranslate nohighlight">\( July~10, 2023: \)</span> Deadline for final paper submission.</p></li>
-<li><p><span class="math notranslate nohighlight">\( December~12\ to\ 16, 2023: \)</span> ASRU Workshop and challenge session</p></li>
+<li><p><span class="math notranslate nohighlight">\( December~12\ to\ 16, 2023: \)</span> ASRU Workshop and Challenge Session.</p></li>
</ul>
</section>
<section id="guidelines">
<h2>Guidelines<a class="headerlink" href="#guidelines" title="Permalink to this heading">露</a></h2>
-<p>Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 15, 2023.</p>
-<p><a class="reference external" href="https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link">M2MET2.0 Registration</a></p>
-<p>Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top three submissions to be included in the ASRU2023 Proceedings.</p>
+<p>Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 22, 2023. Participants are also welcome to join the <a class="reference external" href="https://alibaba-damo-academy.github.io/FunASR/m2met2/Contact.html">wechat group</a> of M2MeT2.0 and keep up to date with the latest updates about the challenge.</p>
+<p><a class="reference external" href="https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link">M2MeT2.0 Registration</a></p>
+<p>Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top ranking submissions to be included in the ASRU2023 Proceedings.</p>
</section>
</section>
@@ -184,7 +184,7 @@
<li class="right" >
<a href="index.html" title="ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Introduction</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Organizers.html b/docs/m2met2/_build/html/Organizers.html
index 0a8811e..e500019 100644
--- a/docs/m2met2/_build/html/Organizers.html
+++ b/docs/m2met2/_build/html/Organizers.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Organizers — m2met2 documentation</title>
+ <title>Organizers — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -44,7 +44,7 @@
<li class="right" >
<a href="Rules.html" title="Rules"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Organizers</a></li>
</ul>
</div>
@@ -55,7 +55,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -124,7 +124,7 @@
<section id="organizers">
<h1>Organizers<a class="headerlink" href="#organizers" title="Permalink to this heading">露</a></h1>
-<p><em><strong>Lei Xie, Professor, Northwestern Polytechnical University, China</strong></em></p>
+<p><em><strong>Lei Xie, Professor, AISHELL foundation, China</strong></em></p>
<p>Email: <a class="reference external" href="mailto:lxie%40nwpu.edu.cn">lxie<span>@</span>nwpu<span>.</span>edu<span>.</span>cn</a></p>
<a class="reference internal image-reference" href="_images/lxie.jpeg"><img alt="lxie" src="_images/lxie.jpeg" style="width: 20%;" /></a>
<p><em><strong>Kong Aik Lee, Senior Scientist at Institute for Infocomm Research, A*Star, Singapore</strong></em></p>
@@ -180,7 +180,7 @@
<li class="right" >
<a href="Rules.html" title="Rules"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Organizers</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Rules.html b/docs/m2met2/_build/html/Rules.html
index 5965115..01f79cb 100644
--- a/docs/m2met2/_build/html/Rules.html
+++ b/docs/m2met2/_build/html/Rules.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Rules — m2met2 documentation</title>
+ <title>Rules — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -44,7 +44,7 @@
<li class="right" >
<a href="Baseline.html" title="Baseline"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Rules</a></li>
</ul>
</div>
@@ -55,7 +55,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -165,7 +165,7 @@
<li class="right" >
<a href="Baseline.html" title="Baseline"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Rules</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/Track_setting_and_evaluation.html b/docs/m2met2/_build/html/Track_setting_and_evaluation.html
index 859f444..1cd72d9 100644
--- a/docs/m2met2/_build/html/Track_setting_and_evaluation.html
+++ b/docs/m2met2/_build/html/Track_setting_and_evaluation.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Track & Evaluation — m2met2 documentation</title>
+ <title>Track & Evaluation — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="Dataset.html" title="Datasets"
accesskey="P">previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Track & Evaluation</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -180,7 +180,7 @@
<li class="right" >
<a href="Dataset.html" title="Datasets"
>previous</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Track & Evaluation</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/_images/baseline_result.png b/docs/m2met2/_build/html/_images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2/_build/html/_images/baseline_result.png
+++ b/docs/m2met2/_build/html/_images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2/_build/html/_images/qrcode.png b/docs/m2met2/_build/html/_images/qrcode.png
new file mode 100644
index 0000000..fc4c349
--- /dev/null
+++ b/docs/m2met2/_build/html/_images/qrcode.png
Binary files differ
diff --git a/docs/m2met2/_build/html/_sources/Baseline.md.txt b/docs/m2met2/_build/html/_sources/Baseline.md.txt
index 6f9609b..4e12162 100644
--- a/docs/m2met2/_build/html/_sources/Baseline.md.txt
+++ b/docs/m2met2/_build/html/_sources/Baseline.md.txt
@@ -1,13 +1,34 @@
# Baseline
## Overview
-We will release an E2E SA-ASR~\cite{kanda21b_interspeech} baseline conducted on [FunASR](https://github.com/alibaba-damo-academy/FunASR) at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.
+We will release an E2E SA-ASR baseline conducted on [FunASR](https://github.com/alibaba-damo-academy/FunASR) at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.
## Quick start
-#TODO: fill with the README.md of the baseline
+To run the baseline, first you need to install FunASR and ModelScope. ([installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html))
+There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.
+Before running `run.sh`, you must manually download and unpack the [AliMeeting](http://www.openslr.org/119/) corpus and place it in the `./dataset` directory:
+```shell
+dataset
+|鈥斺�� Eval_Ali_far
+|鈥斺�� Eval_Ali_near
+|鈥斺�� Test_Ali_far
+|鈥斺�� Test_Ali_near
+|鈥斺�� Train_Ali_far
+|鈥斺�� Train_Ali_near
+```
+Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
+```shell
+data/Test_2023_Ali_far
+|鈥斺�� wav.scp
+|鈥斺�� wav_raw.scp
+|鈥斺�� segments
+|鈥斺�� utt2spk
+|鈥斺�� spk2utt
+```
+For more details you can see [here](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## Baseline results
The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/m2met2/_build/html/_sources/Contact.md.txt b/docs/m2met2/_build/html/_sources/Contact.md.txt
index 3097ad7..6aa3bb7 100644
--- a/docs/m2met2/_build/html/_sources/Contact.md.txt
+++ b/docs/m2met2/_build/html/_sources/Contact.md.txt
@@ -1,9 +1,9 @@
# Contact
-If you have any questions about M2MET2.0 challenge, please contact us by
+If you have any questions about M2MeT2.0 challenge, please contact us by
- email: [m2met.alimeeting@gmail.com](mailto:m2met.alimeeting@gmail.com)
| Wechat group |
|:------------------------------------------:|
-<!-- | <img src="images/wechat.png" width="300"/> | -->
+| <img src="images/qrcode.png" width="300"/> |
diff --git a/docs/m2met2/_build/html/_sources/Introduction.md.txt b/docs/m2met2/_build/html/_sources/Introduction.md.txt
index eac9eb6..fc7c356 100644
--- a/docs/m2met2/_build/html/_sources/Introduction.md.txt
+++ b/docs/m2met2/_build/html/_sources/Introduction.md.txt
@@ -6,23 +6,23 @@
The ICASSP2022 M2MeT challenge focuses on meeting scenarios, and it comprises two main tasks: speaker diarization and multi-speaker automatic speech recognition. The former involves identifying who spoke when in the meeting, while the latter aims to transcribe speech from multiple speakers simultaneously, which poses significant technical difficulties due to overlapping speech and acoustic interferences.
-Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying "who spoke what at when". To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models' performance and advance the state of the art in this area.
+Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU 2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying "who spoke what at when". To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models' performance and advance the state of the art in this area.
## Timeline(AOE Time)
- $ April~29, 2023: $ Challenge and registration open.
-- $ May~8, 2023: $ Baseline release.
-- $ May~15, 2023: $ Registration deadline, the due date for participants to join the Challenge.
-- $ June~9, 2023: $ Test data release and leaderboard open.
-- $ June~13, 2023: $ Final submission deadline.
-- $ June~19, 2023: $ Evaluation result and ranking release.
+- $ May~11, 2023: $ Baseline release.
+- $ May~22, 2023: $ Registration deadline, the due date for participants to join the Challenge.
+- $ June~16, 2023: $ Test data release and leaderboard open.
+- $ June~20, 2023: $ Final submission deadline and leaderboar close.
+- $ June~26, 2023: $ Evaluation result and ranking release.
- $ July~3, 2023: $ Deadline for paper submission.
- $ July~10, 2023: $ Deadline for final paper submission.
-- $ December~12\ to\ 16, 2023: $ ASRU Workshop and challenge session
+- $ December~12\ to\ 16, 2023: $ ASRU Workshop and Challenge Session.
## Guidelines
-Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 15, 2023.
+Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 22, 2023. Participants are also welcome to join the [wechat group](https://alibaba-damo-academy.github.io/FunASR/m2met2/Contact.html) of M2MeT2.0 and keep up to date with the latest updates about the challenge.
-[M2MET2.0 Registration](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
+[M2MeT2.0 Registration](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
-Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top three submissions to be included in the ASRU2023 Proceedings.
+Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top ranking submissions to be included in the ASRU2023 Proceedings.
diff --git a/docs/m2met2/_build/html/_sources/Organizers.md.txt b/docs/m2met2/_build/html/_sources/Organizers.md.txt
index e16c803..f5a9da2 100644
--- a/docs/m2met2/_build/html/_sources/Organizers.md.txt
+++ b/docs/m2met2/_build/html/_sources/Organizers.md.txt
@@ -1,5 +1,5 @@
# Organizers
-***Lei Xie, Professor, Northwestern Polytechnical University, China***
+***Lei Xie, Professor, AISHELL foundation, China***
Email: [lxie@nwpu.edu.cn](mailto:lxie@nwpu.edu.cn)
diff --git a/docs/m2met2/_build/html/genindex.html b/docs/m2met2/_build/html/genindex.html
index e7e17b6..b331f6f 100644
--- a/docs/m2met2/_build/html/genindex.html
+++ b/docs/m2met2/_build/html/genindex.html
@@ -14,7 +14,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Index — m2met2 documentation</title>
+ <title>Index — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -35,7 +35,7 @@
<li class="right" style="margin-right: 10px">
<a href="#" title="General Index"
accesskey="I">index</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Index</a></li>
</ul>
</div>
@@ -46,7 +46,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -132,7 +132,7 @@
<li class="right" style="margin-right: 10px">
<a href="#" title="General Index"
>index</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Index</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/index.html b/docs/m2met2/_build/html/index.html
index dcbb8cb..dd2a9cc 100644
--- a/docs/m2met2/_build/html/index.html
+++ b/docs/m2met2/_build/html/index.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0) — m2met2 documentation</title>
+ <title>ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0) — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -40,7 +40,7 @@
<li class="right" >
<a href="Introduction.html" title="Introduction"
accesskey="N">next</a> |</li>
- <li class="nav-item nav-item-0"><a href="#">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="#">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)</a></li>
</ul>
</div>
@@ -51,7 +51,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- #" class="text-logo">m2met2 documentation</a>
+ #" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -160,7 +160,7 @@
<li class="right" >
<a href="Introduction.html" title="Introduction"
>next</a> |</li>
- <li class="nav-item nav-item-0"><a href="#">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="#">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/objects.inv b/docs/m2met2/_build/html/objects.inv
index 393198c..d8a5ea5 100644
--- a/docs/m2met2/_build/html/objects.inv
+++ b/docs/m2met2/_build/html/objects.inv
@@ -1,5 +1,5 @@
# Sphinx inventory version 2
-# Project: m2met2
+# Project: MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0
# Version:
# The remainder of this file is compressed using zlib.
x趨怉O�0秋�飀衾2矜�!橫�#� <-�6@鞀乥湡迬�７鲼~�鱚迒
B禞罓�#�*頰阖G �;ョ奀辺b赿咰謕�a帍昻;5风�7蒗5S項鑷箉∞+F)�|曵瑉;樶篣鮼)~ L庫z兛<踜2�� 巎排缭H瞁!檄<�1|~骀蛯�,�撒)臕� 挙顥G}�,I(&[燛D矢�9�;芁觿lWk竿翷P蠛C菐�藏�)�;937椔�8薕�1譡�龙猋-硻抑sV �
�,�
\ No newline at end of file
diff --git a/docs/m2met2/_build/html/search.html b/docs/m2met2/_build/html/search.html
index 71adf36..f91b51a 100644
--- a/docs/m2met2/_build/html/search.html
+++ b/docs/m2met2/_build/html/search.html
@@ -14,7 +14,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Search — m2met2 documentation</title>
+ <title>Search — MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
@@ -41,7 +41,7 @@
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="General Index"
accesskey="I">index</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Search</a></li>
</ul>
</div>
@@ -52,7 +52,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 documentation</a>
+ index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-toc">
@@ -149,7 +149,7 @@
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="General Index"
>index</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 documentation</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">Search</a></li>
</ul>
</div>
diff --git a/docs/m2met2/_build/html/searchindex.js b/docs/m2met2/_build/html/searchindex.js
index 54443a0..3387db5 100644
--- a/docs/m2met2/_build/html/searchindex.js
+++ b/docs/m2met2/_build/html/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["Baseline", "Contact", "Dataset", "Introduction", "Organizers", "Rules", "Track_setting_and_evaluation", "index"], "filenames": ["Baseline.md", "Contact.md", "Dataset.md", "Introduction.md", "Organizers.md", "Rules.md", "Track_setting_and_evaluation.md", "index.rst"], "titles": ["Baseline", "Contact", "Datasets", "Introduction", "Organizers", "Rules", "Track & Evaluation", "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"], "terms": {"we": [0, 2, 3, 7], "releas": [0, 2, 3, 6], "an": [0, 2, 3, 6], "e2": 0, "sa": 0, "asr": [0, 3, 7], "cite": 0, "kanda21b_interspeech": 0, "conduct": [0, 2], "funasr": 0, "time": [0, 6], "accord": [0, 3], "timelin": [0, 2], "The": [0, 2, 3, 5, 6], "model": [0, 2, 3, 5, 6], "architectur": 0, "i": [0, 2, 3, 5], "shown": [0, 2], "figur": [0, 6], "3": [0, 2, 3], "speakerencod": 0, "initi": 0, "pre": [0, 6], "train": [0, 3, 5, 7], "speaker": [0, 2, 3, 7], "verif": 0, "from": [0, 2, 3, 5, 6], "modelscop": [0, 6], "thi": [0, 3, 5, 6], "also": [0, 2, 6], "us": [0, 2, 5, 6], "extract": 0, "embed": 0, "profil": 0, "todo": 0, "fill": 0, "readm": 0, "md": 0, "system": [0, 3, 5, 6, 7], "ar": [0, 2, 3, 5, 6, 7], "tabl": [0, 2], "adopt": 0, "oracl": [0, 6], "dure": [0, 2, 6], "howev": [0, 3, 6], "due": [0, 3], "lack": 0, "label": [0, 5, 6], "evalu": [0, 2, 3, 7], "provid": [0, 2, 6, 7], "addit": [0, 6], "spectral": 0, "cluster": 0, "meanwhil": 0, "eval": [0, 2, 5, 6], "test": [0, 2, 3, 5, 6], "set": [0, 2, 3, 5, 6], "show": 0, "impact": 0, "accuraci": [0, 6], "If": [1, 5, 6], "you": 1, "have": [1, 3], "ani": [1, 5, 6], "question": 1, "about": 1, "m2met2": [1, 3], "0": [1, 2, 3], "challeng": [1, 3, 5, 6], "pleas": 1, "u": [1, 2], "email": [1, 3, 4], "m2met": [1, 3, 6, 7], "alimeet": [1, 6], "gmail": 1, "com": [1, 4], "wechat": 1, "group": [1, 2], "In": [2, 3, 5], "fix": [2, 3, 7], "condit": [2, 3, 7], "restrict": 2, "three": [2, 3, 6], "publicli": [2, 6], "avail": [2, 6], "corpora": 2, "name": 2, "aishel": [2, 4, 6], "4": [2, 6], "cn": [2, 4, 6], "celeb": [2, 6], "To": [2, 3, 7], "perform": [2, 3], "new": [2, 3, 6], "call": 2, "2023": [2, 3, 5, 6], "score": [2, 6], "rank": [2, 3, 6], "describ": 2, "contain": [2, 6], "118": 2, "75": 2, "hour": [2, 3, 6], "speech": [2, 3, 6, 7], "total": [2, 6], "divid": [2, 6], "104": 2, "10": [2, 3, 6], "specif": [2, 6], "212": 2, "8": [2, 3], "20": 2, "session": [2, 3, 6, 7], "respect": 2, "each": [2, 3, 6], "consist": [2, 6], "15": [2, 3], "30": 2, "minut": 2, "discuss": 2, "particip": [2, 5, 6], "number": [2, 3, 6], "456": 2, "25": 2, "60": 2, "balanc": 2, "gender": 2, "coverag": 2, "collect": 2, "13": [2, 3], "meet": [2, 3, 6], "venu": 2, "which": [2, 3, 6], "categor": 2, "type": 2, "small": 2, "medium": 2, "larg": [2, 3], "room": [2, 3], "size": 2, "rang": 2, "m": 2, "2": [2, 6], "55": 2, "differ": [2, 3, 6], "give": 2, "varieti": 2, "acoust": [2, 3, 6], "properti": 2, "layout": 2, "paramet": [2, 5], "togeth": 2, "wall": 2, "materi": 2, "cover": 2, "cement": 2, "glass": 2, "etc": 2, "other": 2, "furnish": 2, "includ": [2, 3, 5, 6], "sofa": 2, "tv": 2, "blackboard": 2, "fan": 2, "air": 2, "condition": 2, "plant": 2, "record": [2, 6], "sit": 2, "around": 2, "microphon": [2, 3], "arrai": [2, 3], "place": 2, "natur": 2, "convers": 2, "distanc": 2, "5": 2, "all": [2, 3, 5, 6], "nativ": 2, "chines": 2, "speak": [2, 3], "mandarin": [2, 3], "without": 2, "strong": 2, "accent": 2, "variou": [2, 3], "kind": 2, "indoor": 2, "nois": [2, 3, 5], "limit": [2, 3, 5], "click": 2, "keyboard": 2, "door": 2, "open": [2, 3, 7], "close": 2, "bubbl": 2, "made": [2, 3], "For": 2, "both": [2, 6], "requir": [2, 3, 6], "remain": [2, 3], "same": [2, 5], "posit": 2, "There": 2, "overlap": [2, 3], "between": [2, 6], "exampl": 2, "fig": 2, "1": 2, "within": [2, 3], "one": [2, 5], "ensur": 2, "ratio": 2, "select": [2, 3, 5, 6], "topic": 2, "medic": 2, "treatment": 2, "educ": 2, "busi": 2, "organ": [2, 3, 5, 6, 7], "manag": 2, "industri": [2, 3], "product": 2, "daili": 2, "routin": 2, "averag": 2, "42": 2, "27": 2, "34": 2, "76": 2, "more": 2, "A": [2, 4], "distribut": 2, "were": 2, "ident": [2, 6], "compris": [2, 3, 7], "therebi": 2, "share": 2, "similar": 2, "configur": 2, "field": [2, 3, 6], "signal": [2, 3], "headset": 2, "onli": [2, 5, 6], "": [2, 6], "own": 2, "transcrib": [2, 3, 6], "It": [2, 6], "worth": [2, 6], "note": [2, 6], "far": [2, 3], "audio": [2, 3, 6], "synchron": 2, "common": 2, "transcript": [2, 3, 5, 6], "prepar": 2, "textgrid": 2, "format": 2, "inform": [2, 3], "durat": 2, "id": 2, "segment": [2, 6], "timestamp": [2, 6], "mention": 2, "abov": 2, "can": [2, 3, 5, 6], "download": 2, "openslr": 2, "via": 2, "follow": [2, 5], "link": 2, "particularli": 2, "baselin": [2, 3, 7], "conveni": 2, "script": 2, "automat": [3, 7], "recognit": [3, 7], "diariz": 3, "signific": 3, "stride": 3, "recent": 3, "year": 3, "result": 3, "surg": 3, "technologi": 3, "applic": 3, "across": 3, "domain": 3, "present": 3, "uniqu": [3, 6], "complex": [3, 5], "divers": 3, "style": 3, "variabl": 3, "confer": 3, "environment": 3, "reverber": [3, 5], "over": 3, "sever": 3, "been": 3, "advanc": [3, 7], "develop": [3, 6], "rich": 3, "comput": [3, 5], "hear": 3, "multisourc": 3, "environ": 3, "chime": 3, "latest": 3, "iter": 3, "ha": 3, "particular": 3, "focu": 3, "distant": 3, "gener": 3, "topologi": 3, "scenario": 3, "while": 3, "progress": 3, "english": 3, "languag": [3, 5], "barrier": 3, "achiev": 3, "compar": 3, "non": 3, "multimod": 3, "base": 3, "process": [3, 6], "misp": 3, "multi": [3, 6], "channel": 3, "parti": [3, 6], "instrument": 3, "seek": 3, "address": 3, "problem": 3, "visual": 3, "everydai": 3, "home": 3, "focus": 3, "tackl": 3, "issu": 3, "offlin": 3, "icassp2022": 3, "two": [3, 5, 7], "main": 3, "task": [3, 6, 7], "former": 3, "involv": [3, 6], "identifi": 3, "who": 3, "spoke": 3, "when": 3, "latter": 3, "aim": 3, "multipl": [3, 6], "simultan": 3, "pose": [3, 6], "technic": 3, "difficulti": 3, "interfer": 3, "build": [3, 6, 7], "success": [3, 7], "previou": 3, "excit": 3, "propos": [3, 7], "asru2023": [3, 7], "special": [3, 5, 7], "origin": [3, 5], "metric": [3, 7], "wa": [3, 6], "independ": 3, "meant": 3, "could": 3, "determin": 3, "correspond": [3, 5], "further": 3, "current": [3, 7], "talker": [3, 7], "toward": 3, "practic": 3, "attribut": [3, 7], "sub": [3, 5, 7], "track": [3, 5, 7], "what": 3, "facilit": [3, 7], "reproduc": [3, 7], "research": [3, 4, 7], "offer": 3, "comprehens": [3, 7], "overview": [3, 7], "dataset": [3, 5, 6, 7], "rule": [3, 7], "furthermor": 3, "carefulli": 3, "curat": 3, "approxim": [3, 6], "design": 3, "enabl": 3, "valid": 3, "state": [3, 6, 7], "art": [3, 7], "area": 3, "april": 3, "29": 3, "registr": 3, "mai": 3, "deadlin": 3, "date": 3, "join": 3, "june": 3, "9": 3, "data": [3, 5, 6], "leaderboard": 3, "final": [3, 5, 6], "submiss": 3, "19": 3, "juli": 3, "paper": [3, 6], "decemb": 3, "12": 3, "16": 3, "asru": 3, "workshop": 3, "interest": 3, "whether": 3, "academia": 3, "must": [3, 5, 6], "regist": 3, "complet": 3, "googl": 3, "form": 3, "below": 3, "work": 3, "dai": 3, "send": 3, "invit": 3, "elig": [3, 5], "team": 3, "qualifi": 3, "adher": [3, 5], "publish": 3, "page": 3, "prior": 3, "submit": 3, "descript": [3, 6], "document": 3, "detail": [3, 6], "approach": [3, 5], "method": 3, "top": 3, "proceed": 3, "lei": 4, "xie": 4, "professor": 4, "northwestern": 4, "polytechn": 4, "univers": 4, "china": 4, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "senior": 4, "scientist": 4, "institut": 4, "infocomm": 4, "star": 4, "singapor": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yan": 4, "princip": 4, "engin": 4, "alibaba": 4, "yzj": 4, "inc": 4, "shiliang": 4, "zhang": 4, "sly": 4, "zsl": 4, "yanmin": 4, "qian": 4, "shanghai": 4, "jiao": 4, "tong": 4, "yanminqian": 4, "sjtu": 4, "zhuo": 4, "chen": 4, "appli": 4, "microsoft": 4, "usa": 4, "zhuc": 4, "jian": 4, "wu": 4, "wujian": 4, "hui": 4, "bu": 4, "ceo": 4, "foundat": 4, "buhui": 4, "aishelldata": 4, "should": 5, "augment": 5, "allow": [5, 6], "ad": 5, "speed": 5, "perturb": 5, "tone": 5, "chang": 5, "permit": 5, "purpos": 5, "instead": [5, 6], "util": [5, 6], "tune": 5, "violat": 5, "strictli": [5, 6], "prohibit": [5, 6], "fine": 5, "cpcer": [5, 6], "lower": 5, "judg": 5, "superior": 5, "forc": 5, "align": 5, "obtain": [5, 6], "frame": 5, "level": 5, "classif": 5, "basi": 5, "shallow": 5, "fusion": 5, "end": 5, "e": [5, 6], "g": 5, "la": 5, "rnnt": 5, "transform": [5, 6], "come": 5, "right": 5, "interpret": 5, "belong": 5, "case": 5, "circumst": 5, "coordin": 5, "assign": 6, "illustr": 6, "aishell4": 6, "constrain": 6, "sourc": 6, "addition": 6, "corpu": 6, "soon": 6, "simpl": 6, "voic": 6, "activ": 6, "detect": 6, "vad": 6, "concaten": 6, "minimum": 6, "permut": 6, "charact": 6, "error": 6, "rate": 6, "calcul": 6, "step": 6, "firstli": 6, "refer": 6, "hypothesi": 6, "chronolog": 6, "order": 6, "secondli": 6, "cer": 6, "repeat": 6, "possibl": 6, "lowest": 6, "tthe": 6, "insert": 6, "Ins": 6, "substitut": 6, "delet": 6, "del": 6, "output": 6, "text": 6, "frac": 6, "mathcal": 6, "n_": 6, "100": 6, "where": 6, "usag": 6, "third": 6, "hug": 6, "face": 6, "list": 6, "clearli": 6, "privat": 6, "manual": 6, "simul": 6, "thei": 6, "mandatori": 6, "clear": 6, "scheme": 6, "delight": 7, "introduct": 7, "contact": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"baselin": 0, "overview": [0, 2], "quick": 0, "start": 0, "result": 0, "contact": 1, "dataset": 2, "train": [2, 6], "data": 2, "detail": 2, "alimeet": 2, "corpu": 2, "get": 2, "introduct": 3, "call": 3, "particip": 3, "timelin": 3, "aoe": 3, "time": 3, "guidelin": 3, "organ": 4, "rule": 5, "track": 6, "evalu": 6, "speaker": 6, "attribut": 6, "asr": 6, "metric": 6, "sub": 6, "arrang": 6, "i": 6, "fix": 6, "condit": 6, "ii": 6, "open": 6, "asru": 7, "2023": 7, "multi": 7, "channel": 7, "parti": 7, "meet": 7, "transcript": 7, "challeng": 7, "2": 7, "0": 7, "m2met2": 7, "content": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Baseline": [[0, "baseline"]], "Overview": [[0, "overview"]], "Quick start": [[0, "quick-start"]], "Baseline results": [[0, "baseline-results"]], "Contact": [[1, "contact"]], "Datasets": [[2, "datasets"]], "Overview of training data": [[2, "overview-of-training-data"]], "Detail of AliMeeting corpus": [[2, "detail-of-alimeeting-corpus"]], "Get the data": [[2, "get-the-data"]], "Introduction": [[3, "introduction"]], "Call for participation": [[3, "call-for-participation"]], "Timeline(AOE Time)": [[3, "timeline-aoe-time"]], "Guidelines": [[3, "guidelines"]], "Organizers": [[4, "organizers"]], "Rules": [[5, "rules"]], "Track & Evaluation": [[6, "track-evaluation"]], "Speaker-Attributed ASR": [[6, "speaker-attributed-asr"]], "Evaluation metric": [[6, "evaluation-metric"]], "Sub-track arrangement": [[6, "sub-track-arrangement"]], "Sub-track I (Fixed Training Condition):": [[6, "sub-track-i-fixed-training-condition"]], "Sub-track II (Open Training Condition):": [[6, "sub-track-ii-open-training-condition"]], "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)": [[7, "asru-2023-multi-channel-multi-party-meeting-transcription-challenge-2-0-m2met2-0"]], "Contents:": [[7, null]]}, "indexentries": {}})
\ No newline at end of file
+Search.setIndex({"docnames": ["Baseline", "Contact", "Dataset", "Introduction", "Organizers", "Rules", "Track_setting_and_evaluation", "index"], "filenames": ["Baseline.md", "Contact.md", "Dataset.md", "Introduction.md", "Organizers.md", "Rules.md", "Track_setting_and_evaluation.md", "index.rst"], "titles": ["Baseline", "Contact", "Datasets", "Introduction", "Organizers", "Rules", "Track & Evaluation", "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"], "terms": {"we": [0, 2, 3, 7], "releas": [0, 2, 3, 6], "an": [0, 2, 3, 6], "e2": 0, "sa": 0, "asr": [0, 3, 7], "conduct": [0, 2], "funasr": 0, "time": [0, 6], "accord": [0, 3], "timelin": [0, 2], "The": [0, 2, 3, 5, 6], "model": [0, 2, 3, 5, 6], "architectur": 0, "i": [0, 2, 3, 5], "shown": [0, 2], "figur": [0, 6], "3": [0, 2, 3], "speakerencod": 0, "initi": 0, "pre": [0, 6], "train": [0, 3, 5, 7], "speaker": [0, 2, 3, 7], "verif": 0, "from": [0, 2, 3, 5, 6], "modelscop": [0, 6], "thi": [0, 3, 5, 6], "also": [0, 2, 3, 6], "us": [0, 2, 5, 6], "extract": 0, "embed": 0, "profil": 0, "To": [0, 2, 3, 7], "run": 0, "first": 0, "you": [0, 1], "need": 0, "instal": 0, "There": [0, 2], "ar": [0, 2, 3, 5, 6, 7], "two": [0, 3, 5, 7], "startup": 0, "script": [0, 2], "sh": 0, "evalu": [0, 2, 3, 7], "old": 0, "eval": [0, 2, 5, 6], "test": [0, 2, 3, 5, 6], "set": [0, 2, 3, 5, 6], "run_m2met_2023_inf": 0, "infer": 0, "new": [0, 2, 3, 6], "multi": [0, 3, 6], "channel": [0, 3], "parti": [0, 3, 6], "meet": [0, 2, 3, 6], "transcript": [0, 2, 3, 5, 6], "2": [0, 2, 6], "0": [0, 1, 2, 3], "m2met2": [0, 1, 3], "challeng": [0, 1, 3, 5, 6], "befor": 0, "must": [0, 3, 5, 6], "manual": [0, 6], "download": [0, 2], "unpack": 0, "alimeet": [0, 1, 6], "corpu": [0, 6], "place": [0, 2], "dataset": [0, 3, 5, 6, 7], "directori": 0, "eval_ali_far": 0, "eval_ali_near": 0, "test_ali_far": 0, "test_ali_near": 0, "train_ali_far": 0, "train_ali_near": 0, "test_2023_ali_far": 0, "after": 0, "which": [0, 2, 3, 6], "contain": [0, 2, 6], "onli": [0, 2, 5, 6], "raw": 0, "audio": [0, 2, 3, 6], "Then": 0, "put": 0, "given": 0, "wav": 0, "scp": 0, "wav_raw": 0, "segment": [0, 2, 6], "utt2spk": 0, "spk2utt": 0, "data": [0, 3, 5, 6], "For": [0, 2], "more": [0, 2], "detail": [0, 3, 6], "can": [0, 2, 3, 5, 6], "see": 0, "here": 0, "system": [0, 3, 5, 6, 7], "tabl": [0, 2], "adopt": 0, "oracl": [0, 6], "dure": [0, 2, 6], "howev": [0, 3, 6], "due": [0, 3], "lack": 0, "label": [0, 5, 6], "provid": [0, 2, 6, 7], "addit": [0, 6], "spectral": 0, "cluster": 0, "meanwhil": 0, "show": 0, "impact": 0, "accuraci": [0, 6], "If": [1, 5, 6], "have": [1, 3], "ani": [1, 5, 6], "question": 1, "about": [1, 3], "pleas": 1, "u": [1, 2], "email": [1, 3, 4], "m2met": [1, 3, 6, 7], "gmail": 1, "com": [1, 4], "wechat": [1, 3], "group": [1, 2, 3], "In": [2, 3, 5], "fix": [2, 3, 7], "condit": [2, 3, 7], "restrict": 2, "three": [2, 3, 6], "publicli": [2, 6], "avail": [2, 6], "corpora": 2, "name": 2, "aishel": [2, 4, 6], "4": [2, 6], "cn": [2, 4, 6], "celeb": [2, 6], "perform": [2, 3], "call": 2, "2023": [2, 3, 5, 6], "score": [2, 6], "rank": [2, 3, 6], "describ": 2, "118": 2, "75": 2, "hour": [2, 3, 6], "speech": [2, 3, 6, 7], "total": [2, 6], "divid": [2, 6], "104": 2, "10": [2, 3, 6], "specif": [2, 6], "212": 2, "8": 2, "20": [2, 3], "session": [2, 3, 6, 7], "respect": 2, "each": [2, 3, 6], "consist": [2, 6], "15": 2, "30": 2, "minut": 2, "discuss": 2, "particip": [2, 5, 6], "number": [2, 3, 6], "456": 2, "25": 2, "60": 2, "balanc": 2, "gender": 2, "coverag": 2, "collect": 2, "13": 2, "venu": 2, "categor": 2, "type": 2, "small": 2, "medium": 2, "larg": [2, 3], "room": [2, 3], "size": 2, "rang": 2, "m": 2, "55": 2, "differ": [2, 3, 6], "give": 2, "varieti": 2, "acoust": [2, 3, 6], "properti": 2, "layout": 2, "paramet": [2, 5], "togeth": 2, "wall": 2, "materi": 2, "cover": 2, "cement": 2, "glass": 2, "etc": 2, "other": 2, "furnish": 2, "includ": [2, 3, 5, 6], "sofa": 2, "tv": 2, "blackboard": 2, "fan": 2, "air": 2, "condition": 2, "plant": 2, "record": [2, 6], "sit": 2, "around": 2, "microphon": [2, 3], "arrai": [2, 3], "natur": 2, "convers": 2, "distanc": 2, "5": 2, "all": [2, 3, 5, 6], "nativ": 2, "chines": 2, "speak": [2, 3], "mandarin": [2, 3], "without": 2, "strong": 2, "accent": 2, "variou": [2, 3], "kind": 2, "indoor": 2, "nois": [2, 3, 5], "limit": [2, 3, 5], "click": 2, "keyboard": 2, "door": 2, "open": [2, 3, 7], "close": [2, 3], "bubbl": 2, "made": [2, 3], "both": [2, 6], "requir": [2, 3, 6], "remain": [2, 3], "same": [2, 5], "posit": 2, "overlap": [2, 3], "between": [2, 6], "exampl": 2, "fig": 2, "1": 2, "within": [2, 3], "one": [2, 5], "ensur": 2, "ratio": 2, "select": [2, 3, 5, 6], "topic": 2, "medic": 2, "treatment": 2, "educ": 2, "busi": 2, "organ": [2, 3, 5, 6, 7], "manag": 2, "industri": [2, 3], "product": 2, "daili": 2, "routin": 2, "averag": 2, "42": 2, "27": 2, "34": 2, "76": 2, "A": [2, 4], "distribut": 2, "were": 2, "ident": [2, 6], "compris": [2, 3, 7], "therebi": 2, "share": 2, "similar": 2, "configur": 2, "field": [2, 3, 6], "signal": [2, 3], "headset": 2, "": [2, 6], "own": 2, "transcrib": [2, 3, 6], "It": [2, 6], "worth": [2, 6], "note": [2, 6], "far": [2, 3], "synchron": 2, "common": 2, "prepar": 2, "textgrid": 2, "format": 2, "inform": [2, 3], "durat": 2, "id": 2, "timestamp": [2, 6], "mention": 2, "abov": 2, "openslr": 2, "via": 2, "follow": [2, 5], "link": 2, "particularli": 2, "baselin": [2, 3, 7], "conveni": 2, "automat": [3, 7], "recognit": [3, 7], "diariz": 3, "signific": 3, "stride": 3, "recent": 3, "year": 3, "result": 3, "surg": 3, "technologi": 3, "applic": 3, "across": 3, "domain": 3, "present": 3, "uniqu": [3, 6], "complex": [3, 5], "divers": 3, "style": 3, "variabl": 3, "confer": 3, "environment": 3, "reverber": [3, 5], "over": 3, "sever": 3, "been": 3, "advanc": [3, 7], "develop": [3, 6], "rich": 3, "comput": [3, 5], "hear": 3, "multisourc": 3, "environ": 3, "chime": 3, "latest": 3, "iter": 3, "ha": 3, "particular": 3, "focu": 3, "distant": 3, "gener": 3, "topologi": 3, "scenario": 3, "while": 3, "progress": 3, "english": 3, "languag": [3, 5], "barrier": 3, "achiev": 3, "compar": 3, "non": 3, "multimod": 3, "base": 3, "process": [3, 6], "misp": 3, "instrument": 3, "seek": 3, "address": 3, "problem": 3, "visual": 3, "everydai": 3, "home": 3, "focus": 3, "tackl": 3, "issu": 3, "offlin": 3, "icassp2022": 3, "main": 3, "task": [3, 6, 7], "former": 3, "involv": [3, 6], "identifi": 3, "who": 3, "spoke": 3, "when": 3, "latter": 3, "aim": 3, "multipl": [3, 6], "simultan": 3, "pose": [3, 6], "technic": 3, "difficulti": 3, "interfer": 3, "build": [3, 6, 7], "success": [3, 7], "previou": 3, "excit": 3, "propos": [3, 7], "asru": 3, "special": [3, 5, 7], "origin": [3, 5], "metric": [3, 7], "wa": [3, 6], "independ": 3, "meant": 3, "could": 3, "determin": 3, "correspond": [3, 5], "further": 3, "current": [3, 7], "talker": [3, 7], "toward": 3, "practic": 3, "attribut": [3, 7], "sub": [3, 5, 7], "track": [3, 5, 7], "what": 3, "facilit": [3, 7], "reproduc": [3, 7], "research": [3, 4, 7], "offer": 3, "comprehens": [3, 7], "overview": [3, 7], "rule": [3, 7], "furthermor": 3, "carefulli": 3, "curat": 3, "approxim": [3, 6], "design": 3, "enabl": 3, "valid": 3, "state": [3, 6, 7], "art": [3, 7], "area": 3, "april": 3, "29": 3, "registr": 3, "mai": 3, "11": 3, "22": 3, "deadlin": 3, "date": 3, "join": 3, "june": 3, "16": 3, "leaderboard": 3, "final": [3, 5, 6], "submiss": 3, "leaderboar": 3, "26": 3, "juli": 3, "paper": [3, 6], "decemb": 3, "12": 3, "workshop": 3, "interest": 3, "whether": 3, "academia": 3, "regist": 3, "complet": 3, "googl": 3, "form": 3, "below": 3, "welcom": 3, "keep": 3, "up": 3, "updat": 3, "work": 3, "dai": 3, "send": 3, "invit": 3, "elig": [3, 5], "team": 3, "qualifi": 3, "adher": [3, 5], "publish": 3, "page": 3, "prior": 3, "submit": 3, "descript": [3, 6], "document": 3, "approach": [3, 5], "method": 3, "top": 3, "asru2023": [3, 7], "proceed": 3, "lei": 4, "xie": 4, "professor": 4, "foundat": 4, "china": 4, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "senior": 4, "scientist": 4, "institut": 4, "infocomm": 4, "star": 4, "singapor": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yan": 4, "princip": 4, "engin": 4, "alibaba": 4, "yzj": 4, "inc": 4, "shiliang": 4, "zhang": 4, "sly": 4, "zsl": 4, "yanmin": 4, "qian": 4, "shanghai": 4, "jiao": 4, "tong": 4, "univers": 4, "yanminqian": 4, "sjtu": 4, "zhuo": 4, "chen": 4, "appli": 4, "microsoft": 4, "usa": 4, "zhuc": 4, "jian": 4, "wu": 4, "wujian": 4, "hui": 4, "bu": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "should": 5, "augment": 5, "allow": [5, 6], "ad": 5, "speed": 5, "perturb": 5, "tone": 5, "chang": 5, "permit": 5, "purpos": 5, "instead": [5, 6], "util": [5, 6], "tune": 5, "violat": 5, "strictli": [5, 6], "prohibit": [5, 6], "fine": 5, "cpcer": [5, 6], "lower": 5, "judg": 5, "superior": 5, "forc": 5, "align": 5, "obtain": [5, 6], "frame": 5, "level": 5, "classif": 5, "basi": 5, "shallow": 5, "fusion": 5, "end": 5, "e": [5, 6], "g": 5, "la": 5, "rnnt": 5, "transform": [5, 6], "come": 5, "right": 5, "interpret": 5, "belong": 5, "case": 5, "circumst": 5, "coordin": 5, "assign": 6, "illustr": 6, "aishell4": 6, "constrain": 6, "sourc": 6, "addition": 6, "soon": 6, "simpl": 6, "voic": 6, "activ": 6, "detect": 6, "vad": 6, "concaten": 6, "minimum": 6, "permut": 6, "charact": 6, "error": 6, "rate": 6, "calcul": 6, "step": 6, "firstli": 6, "refer": 6, "hypothesi": 6, "chronolog": 6, "order": 6, "secondli": 6, "cer": 6, "repeat": 6, "possibl": 6, "lowest": 6, "tthe": 6, "insert": 6, "Ins": 6, "substitut": 6, "delet": 6, "del": 6, "output": 6, "text": 6, "frac": 6, "mathcal": 6, "n_": 6, "100": 6, "where": 6, "usag": 6, "third": 6, "hug": 6, "face": 6, "list": 6, "clearli": 6, "privat": 6, "simul": 6, "thei": 6, "mandatori": 6, "clear": 6, "scheme": 6, "delight": 7, "introduct": 7, "contact": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"baselin": 0, "overview": [0, 2], "quick": 0, "start": 0, "result": 0, "contact": 1, "dataset": 2, "train": [2, 6], "data": 2, "detail": 2, "alimeet": 2, "corpu": 2, "get": 2, "introduct": 3, "call": 3, "particip": 3, "timelin": 3, "aoe": 3, "time": 3, "guidelin": 3, "organ": 4, "rule": 5, "track": 6, "evalu": 6, "speaker": 6, "attribut": 6, "asr": 6, "metric": 6, "sub": 6, "arrang": 6, "i": 6, "fix": 6, "condit": 6, "ii": 6, "open": 6, "asru": 7, "2023": 7, "multi": 7, "channel": 7, "parti": 7, "meet": 7, "transcript": 7, "challeng": 7, "2": 7, "0": 7, "m2met2": 7, "content": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Baseline": [[0, "baseline"]], "Overview": [[0, "overview"]], "Quick start": [[0, "quick-start"]], "Baseline results": [[0, "baseline-results"]], "Contact": [[1, "contact"]], "Datasets": [[2, "datasets"]], "Overview of training data": [[2, "overview-of-training-data"]], "Detail of AliMeeting corpus": [[2, "detail-of-alimeeting-corpus"]], "Get the data": [[2, "get-the-data"]], "Introduction": [[3, "introduction"]], "Call for participation": [[3, "call-for-participation"]], "Timeline(AOE Time)": [[3, "timeline-aoe-time"]], "Guidelines": [[3, "guidelines"]], "Organizers": [[4, "organizers"]], "Rules": [[5, "rules"]], "Track & Evaluation": [[6, "track-evaluation"]], "Speaker-Attributed ASR": [[6, "speaker-attributed-asr"]], "Evaluation metric": [[6, "evaluation-metric"]], "Sub-track arrangement": [[6, "sub-track-arrangement"]], "Sub-track I (Fixed Training Condition):": [[6, "sub-track-i-fixed-training-condition"]], "Sub-track II (Open Training Condition):": [[6, "sub-track-ii-open-training-condition"]], "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)": [[7, "asru-2023-multi-channel-multi-party-meeting-transcription-challenge-2-0-m2met2-0"]], "Contents:": [[7, null]]}, "indexentries": {}})
\ No newline at end of file
diff --git a/docs/m2met2/conf.py b/docs/m2met2/conf.py
index 19b93f5..9b2a9b5 100644
--- a/docs/m2met2/conf.py
+++ b/docs/m2met2/conf.py
@@ -7,7 +7,7 @@
# -- Project information -----------------------------------------------------
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
-project = 'm2met2'
+project = 'MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0'
copyright = '2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University'
author = 'Speech Lab, Alibaba Group; Audio, Speech and Language Processing Group, Northwestern Polytechnical University'
diff --git a/docs/m2met2/images/baseline_result.png b/docs/m2met2/images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2/images/baseline_result.png
+++ b/docs/m2met2/images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2/images/qrcode.png b/docs/m2met2/images/qrcode.png
new file mode 100644
index 0000000..fc4c349
--- /dev/null
+++ b/docs/m2met2/images/qrcode.png
Binary files differ
diff --git a/docs/m2met2_cn/_build/doctrees/environment.pickle b/docs/m2met2_cn/_build/doctrees/environment.pickle
index fb92f83..8426df6 100644
--- a/docs/m2met2_cn/_build/doctrees/environment.pickle
+++ b/docs/m2met2_cn/_build/doctrees/environment.pickle
Binary files differ
diff --git a/docs/m2met2_cn/_build/doctrees/index.doctree b/docs/m2met2_cn/_build/doctrees/index.doctree
index 77742ac..1677b8b 100644
--- a/docs/m2met2_cn/_build/doctrees/index.doctree
+++ b/docs/m2met2_cn/_build/doctrees/index.doctree
Binary files differ
diff --git "a/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree" "b/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
index f88f67d..e9e895c 100644
--- "a/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
+++ "b/docs/m2met2_cn/_build/doctrees/\345\237\272\347\272\277.doctree"
Binary files differ
diff --git "a/docs/m2met2_cn/_build/doctrees/\347\256\200\344\273\213.doctree" "b/docs/m2met2_cn/_build/doctrees/\347\256\200\344\273\213.doctree"
index 373ee34..595b41e 100644
--- "a/docs/m2met2_cn/_build/doctrees/\347\256\200\344\273\213.doctree"
+++ "b/docs/m2met2_cn/_build/doctrees/\347\256\200\344\273\213.doctree"
Binary files differ
diff --git "a/docs/m2met2_cn/_build/doctrees/\350\201\224\347\263\273\346\226\271\345\274\217.doctree" "b/docs/m2met2_cn/_build/doctrees/\350\201\224\347\263\273\346\226\271\345\274\217.doctree"
index df477c8..6b8208a 100644
--- "a/docs/m2met2_cn/_build/doctrees/\350\201\224\347\263\273\346\226\271\345\274\217.doctree"
+++ "b/docs/m2met2_cn/_build/doctrees/\350\201\224\347\263\273\346\226\271\345\274\217.doctree"
Binary files differ
diff --git "a/docs/m2met2_cn/_build/doctrees/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.doctree" "b/docs/m2met2_cn/_build/doctrees/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.doctree"
index fa83a0c..c6be4ae 100644
--- "a/docs/m2met2_cn/_build/doctrees/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.doctree"
+++ "b/docs/m2met2_cn/_build/doctrees/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.doctree"
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/.buildinfo b/docs/m2met2_cn/_build/html/.buildinfo
index 6b8368e..35632ee 100644
--- a/docs/m2met2_cn/_build/html/.buildinfo
+++ b/docs/m2met2_cn/_build/html/.buildinfo
@@ -1,4 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 5462207d1656a9ae4ca43c2890d094be
+config: 06d9c1d4093817b45b9d4df7ab350eaf
tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/m2met2_cn/_build/html/_images/baseline_result.png b/docs/m2met2_cn/_build/html/_images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2_cn/_build/html/_images/baseline_result.png
+++ b/docs/m2met2_cn/_build/html/_images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/_images/qrcode.png b/docs/m2met2_cn/_build/html/_images/qrcode.png
new file mode 100644
index 0000000..fc4c349
--- /dev/null
+++ b/docs/m2met2_cn/_build/html/_images/qrcode.png
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/_sources/index.rst.txt b/docs/m2met2_cn/_build/html/_sources/index.rst.txt
index c089b36..3d9f241 100644
--- a/docs/m2met2_cn/_build/html/_sources/index.rst.txt
+++ b/docs/m2met2_cn/_build/html/_sources/index.rst.txt
@@ -5,8 +5,8 @@
ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0
==================================================================================
-鍦ㄤ笂涓�灞奙2MET绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖��
-涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
+鍦ㄤ笂涓�灞奙2MeT绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖��
+涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆�
.. toctree::
diff --git "a/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt" "b/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
index e4d02f7..e8fc32c 100644
--- "a/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
+++ "b/docs/m2met2_cn/_build/html/_sources/\345\237\272\347\272\277.md.txt"
@@ -5,8 +5,29 @@
## 蹇�熷紑濮�
-#TODO: fill with the README.md of the baseline
-
+棣栧厛闇�瑕佸畨瑁匜unASR鍜孧odelScope. ([installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html))
+鍩虹嚎绯荤粺鏈夎缁冨拰娴嬭瘯涓や釜鑴氭湰,`run.sh`鏄敤浜庤缁冨熀绾跨郴缁熷苟鍦∕2MeT鐨勯獙璇佷笌娴嬭瘯闆嗕笂璇勪及鐨勶紝鑰宍run_m2met_2023_infer.sh`鐢ㄤ簬姝ゆ绔炶禌棰勫寮�鏀剧殑鍏ㄦ柊娴嬭瘯闆嗕笂娴嬭瘯鍚屾椂鐢熸垚绗﹀悎绔炶禌鏈�缁堟彁浜ゆ牸寮忕殑鏂囦欢銆�
+鍦ㄨ繍琛� `run.sh`鍓嶏紝闇�瑕佽嚜琛屼笅杞藉苟瑙ｅ帇[AliMeeting](http://www.openslr.org/119/)鏁版嵁闆嗗苟鏀剧疆浜巂./dataset`鐩綍涓嬶細
+```shell
+dataset
+|鈥斺�� Eval_Ali_far
+|鈥斺�� Eval_Ali_near
+|鈥斺�� Test_Ali_far
+|鈥斺�� Test_Ali_near
+|鈥斺�� Train_Ali_far
+|鈥斺�� Train_Ali_near
+```
+鍦ㄨ繍琛宍run_m2met_2023_infer.sh`鍓�, 闇�瑕佸皢娴嬭瘯闆哷Test_2023_Ali_far`锛堜粎鍖呭惈闊抽锛屽皢浜�6.16鍙戝竷锛夋斁缃簬`./dataset`鐩綍涓嬨�傜劧鍚庡皢涓诲姙鏂规彁渚涚殑`wav.scp`锛宍wav_raw.scp`锛宍segments`锛宍utt2spk`鍜宍spk2utt`鏀剧疆浜巂./data/Test_2023_Ali_far`鐩綍涓嬨��
+```shell
+data/Test_2023_Ali_far
+|鈥斺�� wav.scp
+|鈥斺�� wav_raw.scp
+|鈥斺�� segments
+|鈥斺�� utt2spk
+|鈥斺�� spk2utt
+```
+鏇村鍩虹嚎绯荤粺璇︽儏瑙乕姝ゅ](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## 鍩虹嚎缁撴灉
鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-
\ No newline at end of file
+
+
\ No newline at end of file
diff --git "a/docs/m2met2_cn/_build/html/_sources/\347\256\200\344\273\213.md.txt" "b/docs/m2met2_cn/_build/html/_sources/\347\256\200\344\273\213.md.txt"
index 52df97d..be456ff 100644
--- "a/docs/m2met2_cn/_build/html/_sources/\347\256\200\344\273\213.md.txt"
+++ "b/docs/m2met2_cn/_build/html/_sources/\347\256\200\344\273\213.md.txt"
@@ -1,32 +1,33 @@
# 绠�浠�
## 绔炶禌浠嬬粛
+
璇煶璇嗗埆锛圓utomatic Speech Recognition锛夈�佽璇濅汉鏃ュ織锛圫peaker Diarization锛夌瓑璇煶澶勭悊鎶�鏈殑鏈�鏂板彂灞曟縺鍙戜簡浼楀鏅鸿兘璇煶鐨勫箍娉涘簲鐢ㄣ�傜劧鑰屼細璁満鏅敱浜庡叾澶嶆潅鐨勫０瀛︽潯浠跺拰涓嶅悓鐨勮璇濋鏍硷紝鍖呮嫭閲嶅彔鐨勮璇濄�佷笉鍚屾暟閲忕殑鍙戣█鑰呫�佸ぇ浼氳瀹ょ殑杩滃満淇″彿浠ュ強鐜鍣０鍜屾贩鍝嶏紝浠嶇劧灞炰簬涓�椤规瀬鍏锋寫鎴樻�х殑浠诲姟銆�
涓轰簡鎺ㄥ姩浼氳鍦烘櫙璇煶璇嗗埆鐨勫彂灞曪紝宸茬粡鏈夊緢澶氱浉鍏崇殑鎸戞垬璧涳紝濡� Rich Transcription evaluation 鍜� CHIME锛圕omputational Hearing in Multisource Environments锛� 鎸戞垬璧涖�傛渶鏂扮殑CHIME鎸戞垬璧涘叧娉ㄤ簬杩滆窛绂昏嚜鍔ㄨ闊宠瘑鍒拰寮�鍙戣兘鍦ㄥ悇绉嶄笉鍚屾嫇鎵戠粨鏋勭殑闃靛垪鍜屽簲鐢ㄥ満鏅腑閫氱敤鐨勭郴缁熴�傜劧鑰屼笉鍚岃瑷�涔嬮棿鐨勫樊寮傞檺鍒朵簡闈炶嫳璇細璁浆褰曠殑杩涘睍銆侻ISP锛圡ultimodal Information Based Speech Processing锛夊拰M2MeT锛圡ulti-Channel Multi-Party Meeting Transcription锛夋寫鎴樿禌涓烘帹鍔ㄦ櫘閫氳瘽浼氳鍦烘櫙璇煶璇嗗埆鍋氬嚭浜嗚础鐚�侻ISP鎸戞垬璧涗晶閲嶄簬鐢ㄨ鍚妯℃�佺殑鏂规硶瑙ｅ喅鏃ュ父瀹跺涵鐜涓殑杩滆窛绂诲楹﹀厠椋庝俊鍙峰鐞嗛棶棰橈紝鑰孧2MeT鎸戞垬鍒欎晶閲嶄簬瑙ｅ喅绂荤嚎浼氳瀹や腑浼氳杞綍鐨勮闊抽噸鍙犻棶棰樸��
-ASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��
+IASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��
-鍦ㄤ笂涓�灞奙2MET鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MET鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
-涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
+鍦ㄤ笂涓�灞奙2MeT鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU 2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MeT鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
+涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆傛澶栵紝鎴戜滑灏嗘牴鎹椂闂磋〃鍙戝竷涓�涓叏鏂扮殑娴嬭瘯闆嗭紝鍖呮嫭澶х害10灏忔椂鐨勯煶棰戙��
## 鏃堕棿瀹夋帓(AOE鏃堕棿)
- $ 2023.4.29: $ 寮�鏀炬敞鍐�
-- $ 2023.5.8: $ 鍩虹嚎鍙戝竷
-- $ 2023.5.15: $ 娉ㄥ唽鎴
-- $ 2023.6.9: $ 娴嬭瘯闆嗘暟鎹彂甯�
-- $ 2023.6.13: $ 鏈�缁堢粨鏋滄彁浜ゆ埅姝�
-- $ 2023.6.19: $ 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�
-- $ 2023.7.3: $ 璁烘枃鎻愪氦鎴
-- $ 2023.7.10: $ 鏈�缁堢増璁烘枃鎻愪氦鎴
-- $ 2023.12.12: $ ASRU Workshop & challenge session
+- $ 2023.5.11: $ 鍩虹嚎鍙戝竷
+- $ 2023.5.22: $ 娉ㄥ唽鎴
+- $ 2023.6.16: $ 娴嬭瘯闆嗘暟鎹彂甯冿紝鎺掕姒滃紑鏀�
+- $ 2023.6.20: $ 鏈�缁堢粨鏋滄彁浜ゆ埅姝紝鎺掕姒滃叧闂�
+- $ 2023.6.26: $ 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�
+- $ 2023.7.3: $ 璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�
+- $ 2023.7.10: $ 鏈�缁堢増璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�
+- $ 2023.12.12: $ ASRU Workshop & Challenge Session
## 绔炶禌鎶ュ悕
-鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�15鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曪細
+鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�22鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曘�傚悓鏃舵杩庡箍澶у弬璧涜�呭姞鍏瀹樻柟浜ゆ祦寰俊缇(https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html)浜ゆ祦骞跺強鏃惰幏鍙栫珵璧涙渶鏂版秷鎭細
-[M2MET2.0鎶ュ悕](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
+[M2MeT2.0鎶ュ悕](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
-涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗛�夋嫨鍓嶄笁鍚嶇撼鍏SRU2023璁烘枃闆嗐��
\ No newline at end of file
+涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗘帓鍚嶅墠鍒楃殑闃熶紞绾冲叆ASRU2023璁烘枃闆嗐��
\ No newline at end of file
diff --git "a/docs/m2met2_cn/_build/html/_sources/\350\201\224\347\263\273\346\226\271\345\274\217.md.txt" "b/docs/m2met2_cn/_build/html/_sources/\350\201\224\347\263\273\346\226\271\345\274\217.md.txt"
index 5c65ca0..fd8f9a4 100644
--- "a/docs/m2met2_cn/_build/html/_sources/\350\201\224\347\263\273\346\226\271\345\274\217.md.txt"
+++ "b/docs/m2met2_cn/_build/html/_sources/\350\201\224\347\263\273\346\226\271\345\274\217.md.txt"
@@ -1,9 +1,9 @@
# 鑱旂郴鏂瑰紡
-濡傛灉瀵筂2MET2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�
+濡傛灉瀵筂2MeT2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�
- 閭欢: [m2met.alimeeting@gmail.com](mailto:m2met.alimeeting@gmail.com)
-| M2MET2.0绔炶禌瀹樻柟寰俊缇� |
+| M2MeT2.0绔炶禌瀹樻柟寰俊缇� |
|:------------------------------------------:|
-<!-- | <img src="images/wechat.png" width="300"/> | -->
+| <img src="images/qrcode.png" width="300"/> |
diff --git "a/docs/m2met2_cn/_build/html/_sources/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md.txt" "b/docs/m2met2_cn/_build/html/_sources/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md.txt"
index 94a6236..ccfbdf3 100644
--- "a/docs/m2met2_cn/_build/html/_sources/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md.txt"
+++ "b/docs/m2met2_cn/_build/html/_sources/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md.txt"
@@ -1,6 +1,6 @@
# 璧涢亾璁剧疆涓庤瘎浼�
## 璇磋瘽浜虹浉鍏崇殑璇煶璇嗗埆
-璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MET2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��
+璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MeT2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��
diff --git a/docs/m2met2_cn/_build/html/genindex.html b/docs/m2met2_cn/_build/html/genindex.html
index 5558bcf..1eee622 100644
--- a/docs/m2met2_cn/_build/html/genindex.html
+++ b/docs/m2met2_cn/_build/html/genindex.html
@@ -14,7 +14,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>绱㈠紩 — m2met2 鏂囨。</title>
+ <title>绱㈠紩 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -36,7 +36,7 @@
<li class="right" style="margin-right: 10px">
<a href="#" title="鎬荤储寮�"
accesskey="I">绱㈠紩</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绱㈠紩</a></li>
</ul>
</div>
@@ -47,7 +47,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -133,7 +133,7 @@
<li class="right" style="margin-right: 10px">
<a href="#" title="鎬荤储寮�"
>绱㈠紩</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绱㈠紩</a></li>
</ul>
</div>
diff --git a/docs/m2met2_cn/_build/html/index.html b/docs/m2met2_cn/_build/html/index.html
index fbc2fce..b7672cf 100644
--- a/docs/m2met2_cn/_build/html/index.html
+++ b/docs/m2met2_cn/_build/html/index.html
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0 — m2met2 鏂囨。</title>
+ <title>ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -41,7 +41,7 @@
<li class="right" >
<a href="%E7%AE%80%E4%BB%8B.html" title="绠�浠�"
accesskey="N">涓嬩竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="#">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="#">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0</a></li>
</ul>
</div>
@@ -52,7 +52,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- #" class="text-logo">m2met2 鏂囨。</a>
+ #" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -121,8 +121,8 @@
<section id="asru-2023-2-0">
<h1>ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0<a class="headerlink" href="#asru-2023-2-0" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h1>
-<p>鍦ㄤ笂涓�灞奙2MET绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖��
-涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
+<p>鍦ㄤ笂涓�灞奙2MeT绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖��
+涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆�</p>
<div class="toctree-wrapper compound">
<p class="caption" role="heading"><span class="caption-text">鐩綍:</span></p>
@@ -161,7 +161,7 @@
<li class="right" >
<a href="%E7%AE%80%E4%BB%8B.html" title="绠�浠�"
>涓嬩竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="#">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="#">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0</a></li>
</ul>
</div>
diff --git a/docs/m2met2_cn/_build/html/objects.inv b/docs/m2met2_cn/_build/html/objects.inv
index 89341d3..d846652 100644
--- a/docs/m2met2_cn/_build/html/objects.inv
+++ b/docs/m2met2_cn/_build/html/objects.inv
Binary files differ
diff --git a/docs/m2met2_cn/_build/html/search.html b/docs/m2met2_cn/_build/html/search.html
index 4fe0684..ca234a0 100644
--- a/docs/m2met2_cn/_build/html/search.html
+++ b/docs/m2met2_cn/_build/html/search.html
@@ -14,7 +14,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>鎼滅储 — m2met2 鏂囨。</title>
+ <title>鎼滅储 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
@@ -42,7 +42,7 @@
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="鎬荤储寮�"
accesskey="I">绱㈠紩</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鎼滅储</a></li>
</ul>
</div>
@@ -53,7 +53,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-toc">
@@ -149,7 +149,7 @@
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="鎬荤储寮�"
>绱㈠紩</a></li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鎼滅储</a></li>
</ul>
</div>
diff --git a/docs/m2met2_cn/_build/html/searchindex.js b/docs/m2met2_cn/_build/html/searchindex.js
index c9fe167..2e211ff 100644
--- a/docs/m2met2_cn/_build/html/searchindex.js
+++ b/docs/m2met2_cn/_build/html/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["index", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "filenames": ["index.rst", "\u57fa\u7ebf.md", "\u6570\u636e\u96c6.md", "\u7b80\u4ecb.md", "\u7ec4\u59d4\u4f1a.md", "\u8054\u7cfb\u65b9\u5f0f.md", "\u89c4\u5219.md", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30.md"], "titles": ["ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u7ade\u8d5b\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "terms": {"m2met": [0, 3, 5, 7], "asru2023": [0, 3], "m2met2": [0, 3, 5, 7], "funasr": 1, "sa": 1, "asr": [1, 3, 7], "speakerencod": 1, "modelscop": [1, 7], "todo": 1, "fill": 1, "with": 1, "the": 1, "readm": 1, "md": 1, "of": 1, "baselin": [1, 2], "aishel": [2, 7], "cn": [2, 4, 7], "celeb": [2, 7], "test": [2, 6, 7], "2023": [2, 3, 6, 7], "118": 2, "75": 2, "104": 2, "train": 2, "eval": [2, 6], "10": [2, 3, 7], "212": 2, "15": [2, 3], "30": 2, "456": 2, "25": 2, "13": [2, 3], "55": 2, "42": 2, "27": 2, "34": 2, "76": 2, "20": 2, "textgrid": 2, "id": 2, "openslr": 2, "automat": 3, "speech": 3, "recognit": 3, "speaker": 3, "diariz": 3, "rich": 3, "transcript": 3, "evalu": 3, "chime": 3, "comput": 3, "hear": 3, "in": 3, "multisourc": 3, "environ": 3, "misp": 3, "multimod": 3, "inform": 3, "base": 3, "process": 3, "multi": 3, "channel": 3, "parti": 3, "meet": 3, "assp2022": 3, "29": 3, "19": 3, "12": 3, "asru": 3, "workshop": 3, "challeng": 3, "session": 3, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "star": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yzj": 4, "alibaba": 4, "inc": 4, "com": [4, 5], "sli": 4, "zsl": 4, "yanminqian": 4, "sjtu": 4, "zhuc": 4, "microsoft": 4, "wujian": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "alimeet": [5, 7], "gmail": 5, "cpcer": [6, 7], "las": 6, "rnnt": 6, "transform": 6, "aishell4": 7, "vad": 7, "cer": 7, "ins": 7, "sub": 7, "del": 7, "text": 7, "frac": 7, "mathcal": 7, "n_": 7, "total": 7, "time": 7, "100": 7, "hug": 7, "face": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"asru": 0, "2023": 0, "alimeet": 2, "aoe": 3}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0": [[0, "asru-2023-2-0"]], "\u76ee\u5f55:": [[0, null]], "\u57fa\u7ebf": [[1, "id1"]], "\u57fa\u7ebf\u6982\u8ff0": [[1, "id2"]], "\u5feb\u901f\u5f00\u59cb": [[1, "id3"]], "\u57fa\u7ebf\u7ed3\u679c": [[1, "id4"]], "\u6570\u636e\u96c6": [[2, "id1"]], "\u6570\u636e\u96c6\u6982\u8ff0": [[2, "id2"]], "Alimeeting\u6570\u636e\u96c6\u4ecb\u7ecd": [[2, "alimeeting"]], "\u83b7\u53d6\u6570\u636e": [[2, "id3"]], "\u7b80\u4ecb": [[3, "id1"]], "\u7ade\u8d5b\u4ecb\u7ecd": [[3, "id2"]], "\u65f6\u95f4\u5b89\u6392(AOE\u65f6\u95f4)": [[3, "aoe"]], "\u7ade\u8d5b\u62a5\u540d": [[3, "id3"]], "\u7ec4\u59d4\u4f1a": [[4, "id1"]], "\u8054\u7cfb\u65b9\u5f0f": [[5, "id1"]], "\u7ade\u8d5b\u89c4\u5219": [[6, "id1"]], "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30": [[7, "id1"]], "\u8bf4\u8bdd\u4eba\u76f8\u5173\u7684\u8bed\u97f3\u8bc6\u522b": [[7, "id2"]], "\u8bc4\u4f30\u65b9\u6cd5": [[7, "id3"]], "\u5b50\u8d5b\u9053\u8bbe\u7f6e": [[7, "id4"]], "\u5b50\u8d5b\u9053\u4e00 (\u9650\u5b9a\u8bad\u7ec3\u6570\u636e):": [[7, "id5"]], "\u5b50\u8d5b\u9053\u4e8c (\u5f00\u653e\u8bad\u7ec3\u6570\u636e):": [[7, "id6"]]}, "indexentries": {}})
\ No newline at end of file
+Search.setIndex({"docnames": ["index", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "filenames": ["index.rst", "\u57fa\u7ebf.md", "\u6570\u636e\u96c6.md", "\u7b80\u4ecb.md", "\u7ec4\u59d4\u4f1a.md", "\u8054\u7cfb\u65b9\u5f0f.md", "\u89c4\u5219.md", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30.md"], "titles": ["ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u7ade\u8d5b\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "terms": {"m2met": [0, 1, 3, 5, 7], "asru2023": [0, 3], "m2met2": [0, 3, 5, 7], "funasr": 1, "sa": 1, "asr": [1, 3, 7], "speakerencod": 1, "modelscop": [1, 7], "instal": 1, "run": 1, "sh": 1, "run_m2met_2023_inf": 1, "alimeet": [1, 5, 7], "dataset": 1, "eval_ali_far": 1, "eval_ali_near": 1, "test_ali_far": 1, "test_ali_near": 1, "train_ali_far": 1, "train_ali_near": 1, "test_2023_ali_far": 1, "16": [1, 3], "wav": 1, "scp": 1, "wav_raw": 1, "segment": 1, "utt2spk": 1, "spk2utt": 1, "data": 1, "aishel": [2, 7], "cn": [2, 4, 7], "celeb": [2, 7], "test": [2, 6, 7], "2023": [2, 3, 6, 7], "118": 2, "75": 2, "104": 2, "train": 2, "eval": [2, 6], "10": [2, 3, 7], "212": 2, "15": 2, "30": 2, "456": 2, "25": 2, "13": 2, "55": 2, "42": 2, "27": 2, "34": 2, "76": 2, "20": [2, 3], "textgrid": 2, "id": 2, "openslr": 2, "baselin": 2, "automat": 3, "speech": 3, "recognit": 3, "speaker": 3, "diariz": 3, "rich": 3, "transcript": 3, "evalu": 3, "chime": 3, "comput": 3, "hear": 3, "in": 3, "multisourc": 3, "environ": 3, "misp": 3, "multimod": 3, "inform": 3, "base": 3, "process": 3, "multi": 3, "channel": 3, "parti": 3, "meet": 3, "iassp2022": 3, "asru": 3, "29": 3, "11": 3, "22": 3, "26": 3, "session": 3, "12": 3, "workshop": 3, "challeng": 3, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "star": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yzj": 4, "alibaba": 4, "inc": 4, "com": [4, 5], "sli": 4, "zsl": 4, "yanminqian": 4, "sjtu": 4, "zhuc": 4, "microsoft": 4, "wujian": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "gmail": 5, "cpcer": [6, 7], "las": 6, "rnnt": 6, "transform": 6, "aishell4": 7, "vad": 7, "cer": 7, "ins": 7, "sub": 7, "del": 7, "text": 7, "frac": 7, "mathcal": 7, "n_": 7, "total": 7, "time": 7, "100": 7, "hug": 7, "face": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"asru": 0, "2023": 0, "alimeet": 2, "aoe": 3}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0": [[0, "asru-2023-2-0"]], "\u76ee\u5f55:": [[0, null]], "\u57fa\u7ebf": [[1, "id1"]], "\u57fa\u7ebf\u6982\u8ff0": [[1, "id2"]], "\u5feb\u901f\u5f00\u59cb": [[1, "id3"]], "\u57fa\u7ebf\u7ed3\u679c": [[1, "id4"]], "\u6570\u636e\u96c6": [[2, "id1"]], "\u6570\u636e\u96c6\u6982\u8ff0": [[2, "id2"]], "Alimeeting\u6570\u636e\u96c6\u4ecb\u7ecd": [[2, "alimeeting"]], "\u83b7\u53d6\u6570\u636e": [[2, "id3"]], "\u7b80\u4ecb": [[3, "id1"]], "\u7ade\u8d5b\u4ecb\u7ecd": [[3, "id2"]], "\u65f6\u95f4\u5b89\u6392(AOE\u65f6\u95f4)": [[3, "aoe"]], "\u7ade\u8d5b\u62a5\u540d": [[3, "id3"]], "\u7ec4\u59d4\u4f1a": [[4, "id1"]], "\u8054\u7cfb\u65b9\u5f0f": [[5, "id1"]], "\u7ade\u8d5b\u89c4\u5219": [[6, "id1"]], "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30": [[7, "id1"]], "\u8bf4\u8bdd\u4eba\u76f8\u5173\u7684\u8bed\u97f3\u8bc6\u522b": [[7, "id2"]], "\u8bc4\u4f30\u65b9\u6cd5": [[7, "id3"]], "\u5b50\u8d5b\u9053\u8bbe\u7f6e": [[7, "id4"]], "\u5b50\u8d5b\u9053\u4e00 (\u9650\u5b9a\u8bad\u7ec3\u6570\u636e):": [[7, "id5"]], "\u5b50\u8d5b\u9053\u4e8c (\u5f00\u653e\u8bad\u7ec3\u6570\u636e):": [[7, "id6"]]}, "indexentries": {}})
\ No newline at end of file
diff --git "a/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html" "b/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
index f28043e..f1afb2d 100644
--- "a/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
+++ "b/docs/m2met2_cn/_build/html/\345\237\272\347\272\277.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>鍩虹嚎 — m2met2 鏂囨。</title>
+ <title>鍩虹嚎 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" title="璧涢亾璁剧疆涓庤瘎浼�"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鍩虹嚎</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -132,12 +132,33 @@
</section>
<section id="id3">
<h2>蹇�熷紑濮�<a class="headerlink" href="#id3" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
-<p>#TODO: fill with the README.md of the baseline</p>
+<p>棣栧厛闇�瑕佸畨瑁匜unASR鍜孧odelScope. (<a class="reference external" href="https://alibaba-damo-academy.github.io/FunASR/en/installation.html">installation</a>)<br />
+鍩虹嚎绯荤粺鏈夎缁冨拰娴嬭瘯涓や釜鑴氭湰,<code class="docutils literal notranslate"><span class="pre">run.sh</span></code>鏄敤浜庤缁冨熀绾跨郴缁熷苟鍦∕2MeT鐨勯獙璇佷笌娴嬭瘯闆嗕笂璇勪及鐨勶紝鑰�<code class="docutils literal notranslate"><span class="pre">run_m2met_2023_infer.sh</span></code>鐢ㄤ簬姝ゆ绔炶禌棰勫寮�鏀剧殑鍏ㄦ柊娴嬭瘯闆嗕笂娴嬭瘯鍚屾椂鐢熸垚绗﹀悎绔炶禌鏈�缁堟彁浜ゆ牸寮忕殑鏂囦欢銆�
+鍦ㄨ繍琛� <code class="docutils literal notranslate"><span class="pre">run.sh</span></code>鍓嶏紝闇�瑕佽嚜琛屼笅杞藉苟瑙ｅ帇<a class="reference external" href="http://www.openslr.org/119/">AliMeeting</a>鏁版嵁闆嗗苟鏀剧疆浜�<code class="docutils literal notranslate"><span class="pre">./dataset</span></code>鐩綍涓嬶細</p>
+<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>dataset
+<span class="p">|</span>鈥斺��<span class="w"> </span>Eval_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Eval_Ali_near
+<span class="p">|</span>鈥斺��<span class="w"> </span>Test_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Test_Ali_near
+<span class="p">|</span>鈥斺��<span class="w"> </span>Train_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>Train_Ali_near
+</pre></div>
+</div>
+<p>鍦ㄨ繍琛�<code class="docutils literal notranslate"><span class="pre">run_m2met_2023_infer.sh</span></code>鍓�, 闇�瑕佸皢娴嬭瘯闆�<code class="docutils literal notranslate"><span class="pre">Test_2023_Ali_far</span></code>锛堜粎鍖呭惈闊抽锛屽皢浜�6.16鍙戝竷锛夋斁缃簬<code class="docutils literal notranslate"><span class="pre">./dataset</span></code>鐩綍涓嬨�傜劧鍚庡皢涓诲姙鏂规彁渚涚殑<code class="docutils literal notranslate"><span class="pre">wav.scp</span></code>锛�<code class="docutils literal notranslate"><span class="pre">wav_raw.scp</span></code>锛�<code class="docutils literal notranslate"><span class="pre">segments</span></code>锛�<code class="docutils literal notranslate"><span class="pre">utt2spk</span></code>鍜�<code class="docutils literal notranslate"><span class="pre">spk2utt</span></code>鏀剧疆浜�<code class="docutils literal notranslate"><span class="pre">./data/Test_2023_Ali_far</span></code>鐩綍涓嬨��</p>
+<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>data/Test_2023_Ali_far
+<span class="p">|</span>鈥斺��<span class="w"> </span>wav.scp
+<span class="p">|</span>鈥斺��<span class="w"> </span>wav_raw.scp
+<span class="p">|</span>鈥斺��<span class="w"> </span>segments
+<span class="p">|</span>鈥斺��<span class="w"> </span>utt2spk
+<span class="p">|</span>鈥斺��<span class="w"> </span>spk2utt
+</pre></div>
+</div>
+<p>鏇村鍩虹嚎绯荤粺璇︽儏瑙�<a class="reference external" href="https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md">姝ゅ</a></p>
</section>
<section id="id4">
<h2>鍩虹嚎缁撴灉<a class="headerlink" href="#id4" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
-<p>鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-<img alt="baseline result" src="_images/baseline_result.png" /></p>
+<p>鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�</p>
+<p><img alt="baseline_result" src="_images/baseline_result.png" /></p>
</section>
</section>
@@ -171,7 +192,7 @@
<li class="right" >
<a href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" title="璧涢亾璁剧疆涓庤瘎浼�"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鍩虹嚎</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\346\225\260\346\215\256\351\233\206.html" "b/docs/m2met2_cn/_build/html/\346\225\260\346\215\256\351\233\206.html"
index ddefcc1..016c58f 100644
--- "a/docs/m2met2_cn/_build/html/\346\225\260\346\215\256\351\233\206.html"
+++ "b/docs/m2met2_cn/_build/html/\346\225\260\346\215\256\351\233\206.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>鏁版嵁闆� — m2met2 鏂囨。</title>
+ <title>鏁版嵁闆� — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="%E7%AE%80%E4%BB%8B.html" title="绠�浠�"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鏁版嵁闆�</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -180,7 +180,7 @@
<li class="right" >
<a href="%E7%AE%80%E4%BB%8B.html" title="绠�浠�"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鏁版嵁闆�</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\347\256\200\344\273\213.html" "b/docs/m2met2_cn/_build/html/\347\256\200\344\273\213.html"
index f1da18e..1f9d560 100644
--- "a/docs/m2met2_cn/_build/html/\347\256\200\344\273\213.html"
+++ "b/docs/m2met2_cn/_build/html/\347\256\200\344\273\213.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>绠�浠� — m2met2 鏂囨。</title>
+ <title>绠�浠� — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -46,7 +46,7 @@
<li class="right" >
<a href="index.html" title="ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绠�浠�</a></li>
</ul>
</div>
@@ -57,7 +57,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -130,30 +130,30 @@
<h2>绔炶禌浠嬬粛<a class="headerlink" href="#id2" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
<p>璇煶璇嗗埆锛圓utomatic Speech Recognition锛夈�佽璇濅汉鏃ュ織锛圫peaker Diarization锛夌瓑璇煶澶勭悊鎶�鏈殑鏈�鏂板彂灞曟縺鍙戜簡浼楀鏅鸿兘璇煶鐨勫箍娉涘簲鐢ㄣ�傜劧鑰屼細璁満鏅敱浜庡叾澶嶆潅鐨勫０瀛︽潯浠跺拰涓嶅悓鐨勮璇濋鏍硷紝鍖呮嫭閲嶅彔鐨勮璇濄�佷笉鍚屾暟閲忕殑鍙戣█鑰呫�佸ぇ浼氳瀹ょ殑杩滃満淇″彿浠ュ強鐜鍣０鍜屾贩鍝嶏紝浠嶇劧灞炰簬涓�椤规瀬鍏锋寫鎴樻�х殑浠诲姟銆�</p>
<p>涓轰簡鎺ㄥ姩浼氳鍦烘櫙璇煶璇嗗埆鐨勫彂灞曪紝宸茬粡鏈夊緢澶氱浉鍏崇殑鎸戞垬璧涳紝濡� Rich Transcription evaluation 鍜� CHIME锛圕omputational Hearing in Multisource Environments锛� 鎸戞垬璧涖�傛渶鏂扮殑CHIME鎸戞垬璧涘叧娉ㄤ簬杩滆窛绂昏嚜鍔ㄨ闊宠瘑鍒拰寮�鍙戣兘鍦ㄥ悇绉嶄笉鍚屾嫇鎵戠粨鏋勭殑闃靛垪鍜屽簲鐢ㄥ満鏅腑閫氱敤鐨勭郴缁熴�傜劧鑰屼笉鍚岃瑷�涔嬮棿鐨勫樊寮傞檺鍒朵簡闈炶嫳璇細璁浆褰曠殑杩涘睍銆侻ISP锛圡ultimodal Information Based Speech Processing锛夊拰M2MeT锛圡ulti-Channel Multi-Party Meeting Transcription锛夋寫鎴樿禌涓烘帹鍔ㄦ櫘閫氳瘽浼氳鍦烘櫙璇煶璇嗗埆鍋氬嚭浜嗚础鐚�侻ISP鎸戞垬璧涗晶閲嶄簬鐢ㄨ鍚妯℃�佺殑鏂规硶瑙ｅ喅鏃ュ父瀹跺涵鐜涓殑杩滆窛绂诲楹﹀厠椋庝俊鍙峰鐞嗛棶棰橈紝鑰孧2MeT鎸戞垬鍒欎晶閲嶄簬瑙ｅ喅绂荤嚎浼氳瀹や腑浼氳杞綍鐨勮闊抽噸鍙犻棶棰樸��</p>
-<p>ASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��</p>
-<p>鍦ㄤ笂涓�灞奙2MET鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MET鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
-涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
+<p>IASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��</p>
+<p>鍦ㄤ笂涓�灞奙2MeT鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU 2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MeT鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
+涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆傛澶栵紝鎴戜滑灏嗘牴鎹椂闂磋〃鍙戝竷涓�涓叏鏂扮殑娴嬭瘯闆嗭紝鍖呮嫭澶х害10灏忔椂鐨勯煶棰戙��</p>
</section>
<section id="aoe">
<h2>鏃堕棿瀹夋帓(AOE鏃堕棿)<a class="headerlink" href="#aoe" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
<ul class="simple">
<li><p><span class="math notranslate nohighlight">\( 2023.4.29: \)</span> 寮�鏀炬敞鍐�</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.5.8: \)</span> 鍩虹嚎鍙戝竷</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.5.15: \)</span> 娉ㄥ唽鎴</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.6.9: \)</span> 娴嬭瘯闆嗘暟鎹彂甯�</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.6.13: \)</span> 鏈�缁堢粨鏋滄彁浜ゆ埅姝�</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.6.19: \)</span> 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.7.3: \)</span> 璁烘枃鎻愪氦鎴</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.7.10: \)</span> 鏈�缁堢増璁烘枃鎻愪氦鎴</p></li>
-<li><p><span class="math notranslate nohighlight">\( 2023.12.12: \)</span> ASRU Workshop & challenge session</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.5.11: \)</span> 鍩虹嚎鍙戝竷</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.5.22: \)</span> 娉ㄥ唽鎴</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.6.16: \)</span> 娴嬭瘯闆嗘暟鎹彂甯冿紝鎺掕姒滃紑鏀�</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.6.20: \)</span> 鏈�缁堢粨鏋滄彁浜ゆ埅姝紝鎺掕姒滃叧闂�</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.6.26: \)</span> 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.7.3: \)</span> 璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.7.10: \)</span> 鏈�缁堢増璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�</p></li>
+<li><p><span class="math notranslate nohighlight">\( 2023.12.12: \)</span> ASRU Workshop & Challenge Session</p></li>
</ul>
</section>
<section id="id3">
<h2>绔炶禌鎶ュ悕<a class="headerlink" href="#id3" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
-<p>鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�15鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曪細</p>
-<p><a class="reference external" href="https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link">M2MET2.0鎶ュ悕</a></p>
-<p>涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗛�夋嫨鍓嶄笁鍚嶇撼鍏SRU2023璁烘枃闆嗐��</p>
+<p>鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�22鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曘�傚悓鏃舵杩庡箍澶у弬璧涜�呭姞鍏�<a class="reference external" href="https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">瀹樻柟浜ゆ祦寰俊缇�</a>浜ゆ祦骞跺強鏃惰幏鍙栫珵璧涙渶鏂版秷鎭細</p>
+<p><a class="reference external" href="https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link">M2MeT2.0鎶ュ悕</a></p>
+<p>涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗘帓鍚嶅墠鍒楃殑闃熶紞绾冲叆ASRU2023璁烘枃闆嗐��</p>
</section>
</section>
@@ -187,7 +187,7 @@
<li class="right" >
<a href="index.html" title="ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绠�浠�</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\347\273\204\345\247\224\344\274\232.html" "b/docs/m2met2_cn/_build/html/\347\273\204\345\247\224\344\274\232.html"
index ddf93bb..e39465f 100644
--- "a/docs/m2met2_cn/_build/html/\347\273\204\345\247\224\344\274\232.html"
+++ "b/docs/m2met2_cn/_build/html/\347\273\204\345\247\224\344\274\232.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>缁勫浼� — m2met2 鏂囨。</title>
+ <title>缁勫浼� — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="绔炶禌瑙勫垯"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">缁勫浼�</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -188,7 +188,7 @@
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="绔炶禌瑙勫垯"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">缁勫浼�</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\350\201\224\347\263\273\346\226\271\345\274\217.html" "b/docs/m2met2_cn/_build/html/\350\201\224\347\263\273\346\226\271\345\274\217.html"
index 249e5dd..fc060e8 100644
--- "a/docs/m2met2_cn/_build/html/\350\201\224\347\263\273\346\226\271\345\274\217.html"
+++ "b/docs/m2met2_cn/_build/html/\350\201\224\347\263\273\346\226\271\345\274\217.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>鑱旂郴鏂瑰紡 — m2met2 鏂囨。</title>
+ <title>鑱旂郴鏂瑰紡 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -41,7 +41,7 @@
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="缁勫浼�"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鑱旂郴鏂瑰紡</a></li>
</ul>
</div>
@@ -52,7 +52,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -121,17 +121,20 @@
<section id="id1">
<h1>鑱旂郴鏂瑰紡<a class="headerlink" href="#id1" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h1>
-<p>濡傛灉瀵筂2MET2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�</p>
+<p>濡傛灉瀵筂2MeT2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�</p>
<ul class="simple">
<li><p>閭欢: <a class="reference external" href="mailto:m2met.alimeeting%40gmail.com">m2met<span>.</span>alimeeting<span>@</span>gmail<span>.</span>com</a></p></li>
</ul>
<table class="docutils align-default">
<thead>
-<tr class="row-odd"><th class="head text-center"><p>M2MET2.0绔炶禌瀹樻柟寰俊缇�</p></th>
+<tr class="row-odd"><th class="head text-center"><p>M2MeT2.0绔炶禌瀹樻柟寰俊缇�</p></th>
</tr>
</thead>
+<tbody>
+<tr class="row-even"><td class="text-center"><p><a class="reference internal" href="_images/qrcode.png"><img alt="_images/qrcode.png" src="_images/qrcode.png" style="width: 300px;" /></a></p></td>
+</tr>
+</tbody>
</table>
-<!-- | <img src="images/wechat.png" width="300"/> | -->
</section>
@@ -158,7 +161,7 @@
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="缁勫浼�"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">鑱旂郴鏂瑰紡</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\350\247\204\345\210\231.html" "b/docs/m2met2_cn/_build/html/\350\247\204\345\210\231.html"
index 5186ebd..7d54533 100644
--- "a/docs/m2met2_cn/_build/html/\350\247\204\345\210\231.html"
+++ "b/docs/m2met2_cn/_build/html/\350\247\204\345\210\231.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>绔炶禌瑙勫垯 — m2met2 鏂囨。</title>
+ <title>绔炶禌瑙勫垯 — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -45,7 +45,7 @@
<li class="right" >
<a href="%E5%9F%BA%E7%BA%BF.html" title="鍩虹嚎"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绔炶禌瑙勫垯</a></li>
</ul>
</div>
@@ -56,7 +56,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -166,7 +166,7 @@
<li class="right" >
<a href="%E5%9F%BA%E7%BA%BF.html" title="鍩虹嚎"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">绔炶禌瑙勫垯</a></li>
</ul>
</div>
diff --git "a/docs/m2met2_cn/_build/html/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.html" "b/docs/m2met2_cn/_build/html/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.html"
index 072ea54..c9a15f9 100644
--- "a/docs/m2met2_cn/_build/html/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.html"
+++ "b/docs/m2met2_cn/_build/html/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.html"
@@ -15,7 +15,7 @@
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>璧涢亾璁剧疆涓庤瘎浼� — m2met2 鏂囨。</title>
+ <title>璧涢亾璁剧疆涓庤瘎浼� — 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
@@ -46,7 +46,7 @@
<li class="right" >
<a href="%E6%95%B0%E6%8D%AE%E9%9B%86.html" title="鏁版嵁闆�"
accesskey="P">涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">璧涢亾璁剧疆涓庤瘎浼�</a></li>
</ul>
</div>
@@ -57,7 +57,7 @@
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
- index.html" class="text-logo">m2met2 鏂囨。</a>
+ index.html" class="text-logo">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
@@ -128,7 +128,7 @@
<h1>璧涢亾璁剧疆涓庤瘎浼�<a class="headerlink" href="#id1" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h1>
<section id="id2">
<h2>璇磋瘽浜虹浉鍏崇殑璇煶璇嗗埆<a class="headerlink" href="#id2" title="姝ゆ爣棰樼殑姘镐箙閾炬帴">露</a></h2>
-<p>璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MET2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��</p>
+<p>璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MeT2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��</p>
<p><img alt="task difference" src="_images/task_diff.png" /></p>
</section>
<section id="id3">
@@ -181,7 +181,7 @@
<li class="right" >
<a href="%E6%95%B0%E6%8D%AE%E9%9B%86.html" title="鏁版嵁闆�"
>涓婁竴椤�</a> |</li>
- <li class="nav-item nav-item-0"><a href="index.html">m2met2 鏂囨。</a> »</li>
+ <li class="nav-item nav-item-0"><a href="index.html">澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0</a> »</li>
<li class="nav-item nav-item-this"><a href="">璧涢亾璁剧疆涓庤瘎浼�</a></li>
</ul>
</div>
diff --git a/docs/m2met2_cn/conf.py b/docs/m2met2_cn/conf.py
index da3a332..b6300d1 100644
--- a/docs/m2met2_cn/conf.py
+++ b/docs/m2met2_cn/conf.py
@@ -7,7 +7,7 @@
# -- Project information -----------------------------------------------------
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
-project = 'm2met2'
+project = '澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬2.0'
copyright = '2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University'
author = 'Speech Lab, Alibaba Group; Audio, Speech and Language Processing Group, Northwestern Polytechnical University'
diff --git a/docs/m2met2_cn/images/baseline_result.png b/docs/m2met2_cn/images/baseline_result.png
index d51d775..6b76361 100644
--- a/docs/m2met2_cn/images/baseline_result.png
+++ b/docs/m2met2_cn/images/baseline_result.png
Binary files differ
diff --git a/docs/m2met2_cn/images/qrcode.png b/docs/m2met2_cn/images/qrcode.png
new file mode 100644
index 0000000..fc4c349
--- /dev/null
+++ b/docs/m2met2_cn/images/qrcode.png
Binary files differ
diff --git a/docs/m2met2_cn/index.rst b/docs/m2met2_cn/index.rst
index c089b36..3d9f241 100644
--- a/docs/m2met2_cn/index.rst
+++ b/docs/m2met2_cn/index.rst
@@ -5,8 +5,8 @@
ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0
==================================================================================
-鍦ㄤ笂涓�灞奙2MET绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖��
-涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
+鍦ㄤ笂涓�灞奙2MeT绔炶禌鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖��
+涓轰簡灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆�
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆�
.. toctree::
diff --git "a/docs/m2met2_cn/\345\237\272\347\272\277.md" "b/docs/m2met2_cn/\345\237\272\347\272\277.md"
index e4d02f7..e8fc32c 100644
--- "a/docs/m2met2_cn/\345\237\272\347\272\277.md"
+++ "b/docs/m2met2_cn/\345\237\272\347\272\277.md"
@@ -5,8 +5,29 @@
## 蹇�熷紑濮�
-#TODO: fill with the README.md of the baseline
-
+棣栧厛闇�瑕佸畨瑁匜unASR鍜孧odelScope. ([installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html))
+鍩虹嚎绯荤粺鏈夎缁冨拰娴嬭瘯涓や釜鑴氭湰,`run.sh`鏄敤浜庤缁冨熀绾跨郴缁熷苟鍦∕2MeT鐨勯獙璇佷笌娴嬭瘯闆嗕笂璇勪及鐨勶紝鑰宍run_m2met_2023_infer.sh`鐢ㄤ簬姝ゆ绔炶禌棰勫寮�鏀剧殑鍏ㄦ柊娴嬭瘯闆嗕笂娴嬭瘯鍚屾椂鐢熸垚绗﹀悎绔炶禌鏈�缁堟彁浜ゆ牸寮忕殑鏂囦欢銆�
+鍦ㄨ繍琛� `run.sh`鍓嶏紝闇�瑕佽嚜琛屼笅杞藉苟瑙ｅ帇[AliMeeting](http://www.openslr.org/119/)鏁版嵁闆嗗苟鏀剧疆浜巂./dataset`鐩綍涓嬶細
+```shell
+dataset
+|鈥斺�� Eval_Ali_far
+|鈥斺�� Eval_Ali_near
+|鈥斺�� Test_Ali_far
+|鈥斺�� Test_Ali_near
+|鈥斺�� Train_Ali_far
+|鈥斺�� Train_Ali_near
+```
+鍦ㄨ繍琛宍run_m2met_2023_infer.sh`鍓�, 闇�瑕佸皢娴嬭瘯闆哷Test_2023_Ali_far`锛堜粎鍖呭惈闊抽锛屽皢浜�6.16鍙戝竷锛夋斁缃簬`./dataset`鐩綍涓嬨�傜劧鍚庡皢涓诲姙鏂规彁渚涚殑`wav.scp`锛宍wav_raw.scp`锛宍segments`锛宍utt2spk`鍜宍spk2utt`鏀剧疆浜巂./data/Test_2023_Ali_far`鐩綍涓嬨��
+```shell
+data/Test_2023_Ali_far
+|鈥斺�� wav.scp
+|鈥斺�� wav_raw.scp
+|鈥斺�� segments
+|鈥斺�� utt2spk
+|鈥斺�� spk2utt
+```
+鏇村鍩虹嚎绯荤粺璇︽儏瑙乕姝ゅ](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
## 鍩虹嚎缁撴灉
鍩虹嚎绯荤粺鐨勭粨鏋滃琛�3鎵�绀恒�傚湪璁粌鏈熼棿锛岃璇濅汉妗ｆ閲囩敤浜嗙湡瀹炶璇濅汉宓屽叆銆傜劧鑰岀敱浜庡湪璇勪及杩囩▼涓己涔忕湡瀹炶璇濅汉鏍囩锛屽洜姝や娇鐢ㄤ簡鐢遍澶栫殑璋辫仛绫绘彁渚涚殑璇磋瘽浜虹壒寰併�傚悓鏃舵垜浠繕鎻愪緵浜嗗湪璇勪及鍜屾祴璇曢泦涓婁娇鐢ㄧ湡瀹炶璇濅汉妗ｆ鐨勭粨鏋滐紝浠ユ樉绀鸿璇濅汉妗ｆ鍑嗙‘鎬х殑褰卞搷銆�
-
\ No newline at end of file
+
+
\ No newline at end of file
diff --git "a/docs/m2met2_cn/\347\256\200\344\273\213.md" "b/docs/m2met2_cn/\347\256\200\344\273\213.md"
index 52df97d..be456ff 100644
--- "a/docs/m2met2_cn/\347\256\200\344\273\213.md"
+++ "b/docs/m2met2_cn/\347\256\200\344\273\213.md"
@@ -1,32 +1,33 @@
# 绠�浠�
## 绔炶禌浠嬬粛
+
璇煶璇嗗埆锛圓utomatic Speech Recognition锛夈�佽璇濅汉鏃ュ織锛圫peaker Diarization锛夌瓑璇煶澶勭悊鎶�鏈殑鏈�鏂板彂灞曟縺鍙戜簡浼楀鏅鸿兘璇煶鐨勫箍娉涘簲鐢ㄣ�傜劧鑰屼細璁満鏅敱浜庡叾澶嶆潅鐨勫０瀛︽潯浠跺拰涓嶅悓鐨勮璇濋鏍硷紝鍖呮嫭閲嶅彔鐨勮璇濄�佷笉鍚屾暟閲忕殑鍙戣█鑰呫�佸ぇ浼氳瀹ょ殑杩滃満淇″彿浠ュ強鐜鍣０鍜屾贩鍝嶏紝浠嶇劧灞炰簬涓�椤规瀬鍏锋寫鎴樻�х殑浠诲姟銆�
涓轰簡鎺ㄥ姩浼氳鍦烘櫙璇煶璇嗗埆鐨勫彂灞曪紝宸茬粡鏈夊緢澶氱浉鍏崇殑鎸戞垬璧涳紝濡� Rich Transcription evaluation 鍜� CHIME锛圕omputational Hearing in Multisource Environments锛� 鎸戞垬璧涖�傛渶鏂扮殑CHIME鎸戞垬璧涘叧娉ㄤ簬杩滆窛绂昏嚜鍔ㄨ闊宠瘑鍒拰寮�鍙戣兘鍦ㄥ悇绉嶄笉鍚屾嫇鎵戠粨鏋勭殑闃靛垪鍜屽簲鐢ㄥ満鏅腑閫氱敤鐨勭郴缁熴�傜劧鑰屼笉鍚岃瑷�涔嬮棿鐨勫樊寮傞檺鍒朵簡闈炶嫳璇細璁浆褰曠殑杩涘睍銆侻ISP锛圡ultimodal Information Based Speech Processing锛夊拰M2MeT锛圡ulti-Channel Multi-Party Meeting Transcription锛夋寫鎴樿禌涓烘帹鍔ㄦ櫘閫氳瘽浼氳鍦烘櫙璇煶璇嗗埆鍋氬嚭浜嗚础鐚�侻ISP鎸戞垬璧涗晶閲嶄簬鐢ㄨ鍚妯℃�佺殑鏂规硶瑙ｅ喅鏃ュ父瀹跺涵鐜涓殑杩滆窛绂诲楹﹀厠椋庝俊鍙峰鐞嗛棶棰橈紝鑰孧2MeT鎸戞垬鍒欎晶閲嶄簬瑙ｅ喅绂荤嚎浼氳瀹や腑浼氳杞綍鐨勮闊抽噸鍙犻棶棰樸��
-ASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��
+IASSP2022 M2MeT鎸戞垬鐨勪晶閲嶇偣鏄細璁満鏅紝瀹冨寘鎷袱涓禌閬擄細璇磋瘽浜烘棩璁板拰澶氳璇濅汉鑷姩璇煶璇嗗埆銆傚墠鑰呮秹鍙婅瘑鍒�滆皝鍦ㄤ粈涔堟椂鍊欒浜嗚瘽鈥濓紝鑰屽悗鑰呮棬鍦ㄥ悓鏃惰瘑鍒潵鑷涓璇濅汉鐨勮闊筹紝璇煶閲嶅彔鍜屽悇绉嶅櫔澹板甫鏉ヤ簡宸ㄥぇ鐨勬妧鏈洶闅俱��
-鍦ㄤ笂涓�灞奙2MET鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU2023涓婄户缁妇鍔濵2MET2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MET鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
-涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MET2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
+鍦ㄤ笂涓�灞奙2MeT鎴愬姛涓惧姙鐨勫熀纭�涓婏紝鎴戜滑灏嗗湪ASRU 2023涓婄户缁妇鍔濵2MeT2.0鎸戞垬璧涖�傚湪涓婁竴灞奙2MeT鎸戞垬璧涗腑锛岃瘎浼版寚鏍囨槸璇磋瘽浜烘棤鍏崇殑锛屾垜浠彧鑳藉緱鍒拌瘑鍒枃鏈紝鑰屼笉鑳界‘瀹氱浉搴旂殑璇磋瘽浜恒��
+涓轰簡瑙ｅ喅杩欎竴灞�闄愭�у苟灏嗙幇鍦ㄧ殑澶氳璇濅汉璇煶璇嗗埆绯荤粺鎺ㄥ悜瀹炵敤鍖栵紝M2MeT2.0鎸戞垬璧涘皢鍦ㄨ璇濅汉鐩稿叧鐨勪汉鐗╀笂璇勪及锛屽苟涓斿悓鏃惰绔嬮檺瀹氭暟鎹笌涓嶉檺瀹氭暟鎹袱涓瓙璧涢亾銆傞�氳繃灏嗚闊冲綊灞炰簬鐗瑰畾鐨勮璇濅汉锛岃繖椤逛换鍔℃棬鍦ㄦ彁楂樺璇磋瘽浜篈SR绯荤粺鍦ㄧ湡瀹炰笘鐣岀幆澧冧腑鐨勫噯纭�у拰閫傜敤鎬с��
鎴戜滑瀵规暟鎹泦銆佽鍒欍�佸熀绾跨郴缁熷拰璇勪及鏂规硶杩涜浜嗚缁嗕粙缁嶏紝浠ヨ繘涓�姝ヤ績杩涘璇磋瘽浜鸿闊宠瘑鍒鍩熺爺绌剁殑鍙戝睍銆傛澶栵紝鎴戜滑灏嗘牴鎹椂闂磋〃鍙戝竷涓�涓叏鏂扮殑娴嬭瘯闆嗭紝鍖呮嫭澶х害10灏忔椂鐨勯煶棰戙��
## 鏃堕棿瀹夋帓(AOE鏃堕棿)
- $ 2023.4.29: $ 寮�鏀炬敞鍐�
-- $ 2023.5.8: $ 鍩虹嚎鍙戝竷
-- $ 2023.5.15: $ 娉ㄥ唽鎴
-- $ 2023.6.9: $ 娴嬭瘯闆嗘暟鎹彂甯�
-- $ 2023.6.13: $ 鏈�缁堢粨鏋滄彁浜ゆ埅姝�
-- $ 2023.6.19: $ 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�
-- $ 2023.7.3: $ 璁烘枃鎻愪氦鎴
-- $ 2023.7.10: $ 鏈�缁堢増璁烘枃鎻愪氦鎴
-- $ 2023.12.12: $ ASRU Workshop & challenge session
+- $ 2023.5.11: $ 鍩虹嚎鍙戝竷
+- $ 2023.5.22: $ 娉ㄥ唽鎴
+- $ 2023.6.16: $ 娴嬭瘯闆嗘暟鎹彂甯冿紝鎺掕姒滃紑鏀�
+- $ 2023.6.20: $ 鏈�缁堢粨鏋滄彁浜ゆ埅姝紝鎺掕姒滃叧闂�
+- $ 2023.6.26: $ 璇勪及缁撴灉鍜屾帓鍚嶅彂甯�
+- $ 2023.7.3: $ 璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�
+- $ 2023.7.10: $ 鏈�缁堢増璁烘枃鎻愪氦鎴锛堥�氳繃ASRU2023瀹樻柟鎶曠锛岄�夋嫨绔炶禌Session锛�
+- $ 2023.12.12: $ ASRU Workshop & Challenge Session
## 绔炶禌鎶ュ悕
-鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�15鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曪細
+鏉ヨ嚜瀛︽湳鐣屽拰宸ヤ笟鐣岀殑鏈夋剰鍚戝弬璧涜�呭潎搴斿湪2023骞�5鏈�22鏃ュ強涔嬪墠濉啓涓嬫柟鐨勮胺姝岃〃鍗曘�傚悓鏃舵杩庡箍澶у弬璧涜�呭姞鍏瀹樻柟浜ゆ祦寰俊缇(https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html)浜ゆ祦骞跺強鏃惰幏鍙栫珵璧涙渶鏂版秷鎭細
-[M2MET2.0鎶ュ悕](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
+[M2MeT2.0鎶ュ悕](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
-涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗛�夋嫨鍓嶄笁鍚嶇撼鍏SRU2023璁烘枃闆嗐��
\ No newline at end of file
+涓诲姙鏂瑰皢鍦�3涓伐浣滄棩鍐呴�氳繃鐢靛瓙閭欢閫氱煡绗﹀悎鏉′欢鐨勫弬璧涘洟闃燂紝鍥㈤槦蹇呴』閬靛畧灏嗗湪鎸戞垬缃戠珯涓婂彂甯冪殑鎸戞垬瑙勫垯銆傚湪鎺掑悕鍙戝竷涔嬪墠锛屾瘡涓弬璧涜�呭繀椤绘彁浜や竴浠界郴缁熸弿杩版枃浠讹紝璇︾粏璇存槑浣跨敤鐨勬柟娉曞拰妯″瀷銆備富鍔炴柟灏嗘帓鍚嶅墠鍒楃殑闃熶紞绾冲叆ASRU2023璁烘枃闆嗐��
\ No newline at end of file
diff --git "a/docs/m2met2_cn/\350\201\224\347\263\273\346\226\271\345\274\217.md" "b/docs/m2met2_cn/\350\201\224\347\263\273\346\226\271\345\274\217.md"
index 5c65ca0..fd8f9a4 100644
--- "a/docs/m2met2_cn/\350\201\224\347\263\273\346\226\271\345\274\217.md"
+++ "b/docs/m2met2_cn/\350\201\224\347\263\273\346\226\271\345\274\217.md"
@@ -1,9 +1,9 @@
# 鑱旂郴鏂瑰紡
-濡傛灉瀵筂2MET2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�
+濡傛灉瀵筂2MeT2.0绔炶禌鏈変换浣曠枒闂紝娆㈣繋閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑锛�
- 閭欢: [m2met.alimeeting@gmail.com](mailto:m2met.alimeeting@gmail.com)
-| M2MET2.0绔炶禌瀹樻柟寰俊缇� |
+| M2MeT2.0绔炶禌瀹樻柟寰俊缇� |
|:------------------------------------------:|
-<!-- | <img src="images/wechat.png" width="300"/> | -->
+| <img src="images/qrcode.png" width="300"/> |
diff --git "a/docs/m2met2_cn/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md" "b/docs/m2met2_cn/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md"
index 94a6236..ccfbdf3 100644
--- "a/docs/m2met2_cn/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md"
+++ "b/docs/m2met2_cn/\350\265\233\351\201\223\350\256\276\347\275\256\344\270\216\350\257\204\344\274\260.md"
@@ -1,6 +1,6 @@
# 璧涢亾璁剧疆涓庤瘎浼�
## 璇磋瘽浜虹浉鍏崇殑璇煶璇嗗埆
-璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MET2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��
+璇磋瘽浜虹浉鍏崇殑ASR浠诲姟闇�瑕佷粠閲嶅彔鐨勮闊充腑璇嗗埆姣忎釜璇磋瘽浜虹殑璇煶锛屽苟涓鸿瘑鍒唴瀹瑰垎閰嶄竴涓璇濅汉鏍囩銆傚浘2灞曠ず浜嗚璇濅汉鐩稿叧璇煶璇嗗埆浠诲姟鍜屽璇磋瘽浜鸿闊宠瘑鍒换鍔＄殑涓昏鍖哄埆銆傚湪鏈绔炶禌涓瑼liMeeting銆丄ishell4鍜孋n-Celeb鏁版嵁闆嗗彲浣滀负鍙楅檺鏁版嵁婧愩�傚湪M2MeT鎸戞垬璧涗腑浣跨敤鐨凙liMeeting鏁版嵁闆嗗寘鍚缁冦�佽瘎浼板拰娴嬭瘯闆嗭紝鍦∕2MeT2.0鍙互鍦ㄨ缁冨拰璇勪及涓娇鐢ㄣ�傛澶栵紝涓�涓寘鍚害10灏忔椂浼氳鏁版嵁鐨勬柊鐨凾est-2023闆嗗皢鏍规嵁璧涚▼瀹夋帓鍙戝竷骞剁敤浜庢寫鎴樿禌鐨勮瘎鍒嗗拰鎺掑悕銆傚�煎緱娉ㄦ剰鐨勬槸锛屽浜嶵est-2023娴嬭瘯闆嗭紝涓诲姙鏂瑰皢涓嶅啀鎻愪緵鑰虫満鐨勮繎鍦洪煶棰戙�佽浆褰曚互鍙婄湡瀹炴椂闂存埑銆傝�屾槸鎻愪緵鍙互閫氳繃涓�涓畝鍗曠殑VAD妯″瀷寰楀埌鐨勫寘鍚涓璇濅汉鐨勭墖娈点��
diff --git a/egs/alimeeting/sa-asr/README.md b/egs/alimeeting/sa-asr/README.md
index 882345c..bc6d04c 100644
--- a/egs/alimeeting/sa-asr/README.md
+++ b/egs/alimeeting/sa-asr/README.md
@@ -19,7 +19,7 @@
stage 7 - 9: Language model training (Optional).
stage 10 - 11: ASR training (SA-ASR requires loading the pre-trained ASR model).
stage 12: SA-ASR training.
-stage 13 - 18: Inference and evaluation.
+stage 13 - 16: Inference and evaluation.
```
Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
```shell
@@ -37,6 +37,10 @@
stage 3: Inference.
stage 4: Generation of SA-ASR results required for final submission.
```
+
+The baseline model is available on [ModelScope](https://www.modelscope.cn/models/damo/speech_saasr_asr-zh-cn-16k-alimeeting/summary).
+After generate stats of AliMeeting corpus(stage 10 in `run.sh`), you can set the `infer_with_pretrained_model=true` in `run.sh` to infer with our official baseline model released on ModelScope without training.
+
# Format of Final Submission
Finally, you need to submit a file called `text_spk_merge` with the following format:
```shell
diff --git a/egs/alimeeting/sa-asr/asr_local.sh b/egs/alimeeting/sa-asr/asr_local.sh
index f8cdcd3..543352e 100755
--- a/egs/alimeeting/sa-asr/asr_local.sh
+++ b/egs/alimeeting/sa-asr/asr_local.sh
@@ -107,8 +107,8 @@
# inference_asr_model=valid.acc.best.pth
# inference_asr_model=valid.loss.ave.pth
inference_sa_asr_model=valid.acc_spk.ave.pb
-download_model= # Download a model from Model Zoo and use it for decoding.
-
+infer_with_pretrained_model=false # Use pretrained model for decoding
+download_sa_asr_model= # Download the SA-ASR model from ModelScope and use it for decoding.
# [Task dependent] Set the datadir name created by local/data.sh
train_set= # Name of training set.
valid_set= # Name of validation set used for monitoring/tuning network training.
@@ -203,7 +203,8 @@
# Note that it will overwrite args in inference config.
--inference_lm # Language modle path for decoding (default="${inference_lm}").
--inference_asr_model # ASR model path for decoding (default="${inference_asr_model}").
- --download_model # Download a model from Model Zoo and use it for decoding (default="${download_model}").
+ --infer_with_pretrained_model # Use pretrained model for decoding (default="${infer_with_pretrained_model}").
+ --download_sa_asr_model= # Download the SA-ASR model from ModelScope and use it for decoding(default="${download_sa_asr_model}").
# [Task dependent] Set the datadir name created by local/data.sh
--train_set # Name of training set (required).
@@ -304,6 +305,9 @@
lm_token_type="${token_type}"
fi
+if ${infer_with_pretrained_model}; then
+ skip_train=true
+fi
# Set tag for naming of model directory
if [ -z "${asr_tag}" ]; then
@@ -1220,119 +1224,20 @@
log "Skip the training stages"
fi
+if ${infer_with_pretrained_model}; then
+ log "Use ${download_sa_asr_model} for decoding and evaluation"
+
+ sa_asr_exp="${expdir}/${download_sa_asr_model}"
+ mkdir -p "${sa_asr_exp}"
+
+ python local/download_pretrained_model_from_modelscope.py $download_sa_asr_model ${expdir}
+ inference_sa_asr_model="model.pb"
+ inference_config=${sa_asr_exp}/decoding.yaml
+fi
if ! "${skip_eval}"; then
if [ ${stage} -le 13 ] && [ ${stop_stage} -ge 13 ]; then
- log "Stage 13: Decoding multi-talker ASR: training_dir=${asr_exp}"
-
- if ${gpu_inference}; then
- _cmd="${cuda_cmd}"
- inference_nj=$[${ngpu}*${njob_infer}]
- _ngpu=1
-
- else
- _cmd="${decode_cmd}"
- inference_nj=$inference_nj
- _ngpu=0
- fi
-
- _opts=
- if [ -n "${inference_config}" ]; then
- _opts+="--config ${inference_config} "
- fi
- if "${use_lm}"; then
- if "${use_word_lm}"; then
- _opts+="--word_lm_train_config ${lm_exp}/config.yaml "
- _opts+="--word_lm_file ${lm_exp}/${inference_lm} "
- else
- _opts+="--lm_train_config ${lm_exp}/config.yaml "
- _opts+="--lm_file ${lm_exp}/${inference_lm} "
- fi
- fi
-
- # 2. Generate run.sh
- log "Generate '${asr_exp}/${inference_tag}/run.sh'. You can resume the process from stage 13 using this script"
- mkdir -p "${asr_exp}/${inference_tag}"; echo "${run_args} --stage 13 \"\$@\"; exit \$?" > "${asr_exp}/${inference_tag}/run.sh"; chmod +x "${asr_exp}/${inference_tag}/run.sh"
-
- for dset in ${test_sets}; do
- _data="${data_feats}/${dset}"
- _dir="${asr_exp}/${inference_tag}/${dset}"
- _logdir="${_dir}/logdir"
- mkdir -p "${_logdir}"
-
- _feats_type="$(<${_data}/feats_type)"
- if [ "${_feats_type}" = raw ]; then
- _scp=wav.scp
- if [[ "${audio_format}" == *ark* ]]; then
- _type=kaldi_ark
- else
- _type=sound
- fi
- else
- _scp=feats.scp
- _type=kaldi_ark
- fi
-
- # 1. Split the key file
- key_file=${_data}/${_scp}
- split_scps=""
- _nj=$(min "${inference_nj}" "$(<${key_file} wc -l)")
- echo $_nj
- for n in $(seq "${_nj}"); do
- split_scps+=" ${_logdir}/keys.${n}.scp"
- done
- # shellcheck disable=SC2086
- utils/split_scp.pl "${key_file}" ${split_scps}
-
- # 2. Submit decoding jobs
- log "Decoding started... log: '${_logdir}/asr_inference.*.log'"
-
- ${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
- python -m funasr.bin.asr_inference_launch \
- --batch_size 1 \
- --mc True \
- --nbest 1 \
- --ngpu "${_ngpu}" \
- --njob ${njob_infer} \
- --gpuid_list ${device} \
- --data_path_and_name_and_type "${_data}/${_scp},speech,${_type}" \
- --key_file "${_logdir}"/keys.JOB.scp \
- --asr_train_config "${asr_exp}"/config.yaml \
- --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
- --output_dir "${_logdir}"/output.JOB \
- --mode asr \
- ${_opts}
-
- # 3. Concatenates the output files from each jobs
- for f in token token_int score text; do
- for i in $(seq "${_nj}"); do
- cat "${_logdir}/output.${i}/1best_recog/${f}"
- done | LC_ALL=C sort -k1 >"${_dir}/${f}"
- done
- done
- fi
-
-
- if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
- log "Stage 14: Scoring multi-talker ASR"
-
- for dset in ${test_sets}; do
- _data="${data_feats}/${dset}"
- _dir="${asr_exp}/${inference_tag}/${dset}"
-
- python utils/proce_text.py ${_data}/text ${_data}/text.proc
- python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
-
- python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
- tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
- cat ${_dir}/text.cer.txt
-
- done
-
- fi
-
- if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
- log "Stage 15: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"
+ log "Stage 13: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"
if ${gpu_inference}; then
_cmd="${cuda_cmd}"
@@ -1423,8 +1328,8 @@
done
fi
- if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
- log "Stage 16: Scoring SA-ASR (oracle profile)"
+ if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
+ log "Stage 14: Scoring SA-ASR (oracle profile)"
for dset in ${test_sets}; do
_data="${data_feats}/${dset}"
@@ -1448,8 +1353,8 @@
fi
- if [ ${stage} -le 17 ] && [ ${stop_stage} -ge 17 ]; then
- log "Stage 17: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
+ if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
+ log "Stage 15: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
if ${gpu_inference}; then
_cmd="${cuda_cmd}"
@@ -1539,8 +1444,8 @@
done
fi
- if [ ${stage} -le 18 ] && [ ${stop_stage} -ge 18 ]; then
- log "Stage 18: Scoring SA-ASR (cluster profile)"
+ if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
+ log "Stage 16: Scoring SA-ASR (cluster profile)"
for dset in ${test_sets}; do
_data="${data_feats}/${dset}"
diff --git a/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py b/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py
new file mode 100644
index 0000000..b4b5412
--- /dev/null
+++ b/egs/alimeeting/sa-asr/local/download_pretrained_model_from_modelscope.py
@@ -0,0 +1,7 @@
+from modelscope.hub.snapshot_download import snapshot_download
+import sys
+
+if __name__ == "__main__":
+ model_tag = sys.argv[1]
+ local_model_dir = sys.argv[2]
+ model_dir = snapshot_download(model_tag, cache_dir=local_model_dir, revision='1.0.0')
\ No newline at end of file
diff --git a/egs/alimeeting/sa-asr/run.sh b/egs/alimeeting/sa-asr/run.sh
index e5297b8..2869164 100755
--- a/egs/alimeeting/sa-asr/run.sh
+++ b/egs/alimeeting/sa-asr/run.sh
@@ -8,8 +8,8 @@
ngpu=4
device="0,1,2,3"
-stage=1
-stop_stage=18
+stage=12
+stop_stage=13
train_set=Train_Ali_far
@@ -18,6 +18,8 @@
asr_config=conf/train_asr_conformer.yaml
sa_asr_config=conf/train_sa_asr_conformer.yaml
inference_config=conf/decode_asr_rnn.yaml
+infer_with_pretrained_model=true
+download_sa_asr_model="damo/speech_saasr_asr-zh-cn-16k-alimeeting"
lm_config=conf/train_lm_transformer.yaml
use_lm=false
@@ -29,6 +31,8 @@
--stop_stage ${stop_stage} \
--gpu_inference true \
--njob_infer 4 \
+ --infer_with_pretrained_model ${infer_with_pretrained_model} \
+ --download_sa_asr_model $download_sa_asr_model \
--asr_exp exp/asr_train_multispeaker_conformer_raw_zh_char_data_alimeeting \
--sa_asr_exp exp/sa_asr_train_conformer_raw_zh_char_data_alimeeting \
--asr_stats_dir exp/asr_stats_multispeaker_conformer_raw_zh_char_data_alimeeting \
--
Gitblit v1.9.1