0. 说明
ForcePPG: 一种基于ForceAlignment的PPG
- 使用Aishell-1+Librispeech ForceAlignment结果训练的ASR, 训练的并不充分, 为了和之前的结果能够对比, 不进行ckpt early stop的替换
- ASR未用到F0, 使用的结构参看:[1] https://blog.csdn.net/u013625492/article/details/109670529 [2] https://blog.csdn.net/u013625492/article/details/109206085 [3] https://blog.csdn.net/u013625492/article/details/109201157
- 效果可能不是最好, 但是作为PPG可以用
1. 提取流程
1.1. Wav
- DataBaker
- LJSpeech
简单的RAW的WAV就可以了
1.2. 提取文件
先说CN-ASR, 再说EN-ASR, 分别生成两个地方的文件夹, 最后调用的时候, 合并成B-PPG
1.2.1. CN-ASR
# 超参数个数:16
hparams = {
'sample_rate': 16000,
'preemphasis': 0.97,
'n_fft': 400,
'hop_length': 160,
'win_length': 400,
'num_mels': 80,
'n_mfcc': 13,
'window': 'hann',
'fmin': 30.,
'fmax': 7600.,
'ref_db': 20,
'min_db': -80.0,
'griffin_lim_power': 1.5,
'griffin_lim_iterations': 60,
'silence_db': -28.0,
'center': True,
}
assert hparams == audio_hparams
MFCC_DIM = 39
PPG_DIM = 218
# in
meta_path = '*.txt'
wav_dir = '*/wavs_16000'
# out1
ppg_dir = './LJSpeech-1.1-Mandarin-PPG/ppg_generate_10ms_by_audio_hjk2'
mfcc_dir = './LJSpeech-1.1-Mandarin-PPG/mfcc_10ms_by_audio_hjk2'
mel_dir = './LJSpeech-1.1-Mandarin-PPG/mel_10ms_by_audio_hjk2'
spec_dir = './LJSpeech-1.1-Mandarin-PPG/spec_10ms_by_audio_hjk2'
rec_wav_dir = './LJSpeech-1.1-Mandarin-PPG/rec_wavs_16000'
os.makedirs(ppg_dir, exist_ok=True)
os.makedirs(mfcc_dir, exist_ok=True)
os.makedirs(mel_dir, exist_ok=True)
os.makedirs(spec_dir, exist_ok=True)
os.makedirs(rec_wav_dir, exist_ok=True)
# out2
STARTED_DATESTRING = "{0:%Y-%m-%dT%H-%M-%S}".format(datetime.now())
good_meta_path = './LJSpeech-1.1-Mandarin-PPG/meta_good_' + STARTED_DATESTRING + '_v3.txt'
f_good_meta = open(good_meta_path, 'w')
# NN->PPG
ckpt_path = './aishell1_ckpt_model_dir/aishell1ASR.ckpt-128000'
- 代码位于/ceph/home/hujk17/ppgs_extractor_10ms_sch_lh_aishell1/extract_ppg_generate_LJSpeech_ForcePPG.py
- 以及/ceph/home/hujk17/ppgs_extractor_10ms_sch_lh_aishell1/extract_ppg_generate_DataBaker_ForcePPG.py
- 生成的mel和PPG在对应位置
1.2.2. EN
略
1.3. PPG文件夹
2. 规范化文档
实验室第三次作业有规范化文档, 网址为: https://github.com/thuhcsi/dpss-exp3-VC-PPG
扫描二维码关注公众号,回复:
12617548 查看本文章
作业文档链接: https://drive.google.com/file/d/1C1Md176LKIkiO9s3VNssQ0hJzvWmZ0gZ/view?usp=sharing
[不用看, 我整理的, 有些乱] PPG来龙去脉: https://drive.google.com/file/d/1BUYsOtiaPzvee1Hrs77X71SjWWi-Zy3A/view?usp=sharing
感谢卢辉, 长河, 王洁, 老师, 还有同学们牛牛牛. 大家的文档确实简洁有水平哈~