| import numpy as np |
|
|
|
|
| def slice_padding_fbank(speech, speech_lengths, vad_segments): |
| speech_list = [] |
| speech_lengths_list = [] |
| for i, segment in enumerate(vad_segments): |
|
|
| bed_idx = int(segment[0][0] * 16) |
| end_idx = min(int(segment[0][1] * 16), speech_lengths[0]) |
| speech_i = speech[0, bed_idx:end_idx] |
| speech_lengths_i = end_idx - bed_idx |
| speech_list.append(speech_i) |
| speech_lengths_list.append(speech_lengths_i) |
| max_len = max(speech_lengths_list) if speech_lengths_list else 0 |
| feats_pad = [] |
| for arr in speech_list: |
| pad_len = max_len - arr.shape[0] |
| if pad_len > 0: |
| arr = np.pad(arr, (0, pad_len), mode="constant") |
| feats_pad.append(arr) |
| feats_pad = np.stack(feats_pad, axis=0) if feats_pad else np.zeros((0, 0), dtype=np.float32) |
| speech_lengths_pad = np.array(speech_lengths_list, dtype=np.int32) |
| return feats_pad, speech_lengths_pad |
|
|
|
|
| def slice_padding_audio_samples(speech, speech_lengths, vad_segments): |
| speech_list = [] |
| speech_lengths_list = [] |
| for i, segment in enumerate(vad_segments): |
| bed_idx = int(segment[0][0] * 16) |
| end_idx = min(int(segment[0][1] * 16), speech_lengths) |
| speech_i = speech[bed_idx:end_idx] |
| speech_lengths_i = end_idx - bed_idx |
| speech_list.append(speech_i) |
| speech_lengths_list.append(speech_lengths_i) |
|
|
| return speech_list, speech_lengths_list |
|
|
|
|
| def merge_vad(vad_result, max_length=15000, min_length=0): |
| new_result = [] |
| if len(vad_result) <= 1: |
| return vad_result |
| time_step = [t[0] for t in vad_result] + [t[1] for t in vad_result] |
| time_step = sorted(list(set(time_step))) |
| if len(time_step) == 0: |
| return [] |
| bg = 0 |
| for i in range(len(time_step) - 1): |
| time = time_step[i] |
| if time_step[i + 1] - bg < max_length: |
| continue |
| if time - bg > min_length: |
| new_result.append([bg, time]) |
| |
| |
| |
| |
| |
| |
| |
| bg = time |
| new_result.append([bg, time_step[-1]]) |
| return new_result |
|
|
