| | |
|---|
| | | /** |
|---|
| | | * Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved. |
|---|
| | | * MIT License (https://opensource.org/licenses/MIT) |
|---|
| | | * Collaborators: zhuzizyf(China Telecom Shanghai) |
|---|
| | | * Contributed by zhuzizyf(China Telecom). |
|---|
| | | */ |
|---|
| | | |
|---|
| | | #pragma once |
|---|
| | | |
|---|
| | | #include <utility> |
|---|
| | | #include <vector> |
|---|
| | |
|---|
| | | #include <numeric> |
|---|
| | | #include <cassert> |
|---|
| | | |
|---|
| | | |
|---|
| | | namespace funasr { |
|---|
| | | enum class VadStateMachine { |
|---|
| | | kVadInStateStartPointNotDetected = 1, |
|---|
| | | kVadInStateInSpeechSegment = 2, |
|---|
| | |
|---|
| | | max_end_sil_frame_cnt_thresh = max_end_sil - vad_opts.speech_to_sil_time_thres; |
|---|
| | | this->waveform = waveform; |
|---|
| | | this->vad_opts.max_single_segment_time = max_single_segment_time; |
|---|
| | | this->vad_opts.speech_noise_thres = speech_noise_thres; |
|---|
| | | this->speech_noise_thres = speech_noise_thres; |
|---|
| | | this->vad_opts.sample_rate = sample_rate; |
|---|
| | | |
|---|
| | | ComputeDecibel(); |
|---|
| | |
|---|
| | | } else { |
|---|
| | | data_buf_all_size += waveform.size(); |
|---|
| | | } |
|---|
| | | for (int offset = 0; offset < waveform.size() - frame_sample_length + 1; offset += frame_shift_length) { |
|---|
| | | for (int offset = 0; offset + frame_sample_length -1 < waveform.size(); offset += frame_shift_length) { |
|---|
| | | float sum = 0.0; |
|---|
| | | for (int i = 0; i < frame_sample_length; i++) { |
|---|
| | | sum += waveform[offset + i] * waveform[offset + i]; |
|---|
| | |
|---|
| | | if (cur_seg.end_ms != start_frm * vad_opts.frame_in_ms) { |
|---|
| | | std::cout << "warning\n"; |
|---|
| | | } |
|---|
| | | int out_pos = (int) cur_seg.buffer.size(); |
|---|
| | | |
|---|
| | | int data_to_pop; |
|---|
| | | if (end_point_is_sent_end) { |
|---|
| | | data_to_pop = expected_sample_number; |
|---|
| | |
|---|
| | | expected_sample_number = data_buf_size; |
|---|
| | | } |
|---|
| | | cur_seg.doa = 0; |
|---|
| | | for (int sample_cpy_out = 0; sample_cpy_out < data_to_pop; sample_cpy_out++) { |
|---|
| | | cur_seg.buffer.push_back(data_buf.back()); |
|---|
| | | out_pos++; |
|---|
| | | } |
|---|
| | | for (int sample_cpy_out = data_to_pop; sample_cpy_out < expected_sample_number; sample_cpy_out++) { |
|---|
| | | cur_seg.buffer.push_back(data_buf.back()); |
|---|
| | | out_pos++; |
|---|
| | | } |
|---|
| | | |
|---|
| | | if (cur_seg.end_ms != start_frm * vad_opts.frame_in_ms) { |
|---|
| | | std::cout << "Something wrong with the VAD algorithm\n"; |
|---|
| | | } |
|---|
| | |
|---|
| | | |
|---|
| | | }; |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | } // namespace funasr |
|---|
