jsut lab

jsut-lab

该存储库为JSUT（日本的Saruwatari-Lab。，Tokyo University of Tokyo University）语料库（V1.1）提供了额外的全文标签HTK/HTS风格的对齐文件。所有对齐文件（.LAB）均通过使用Julius的强制对准提取，并且由OpenJtalk生成全文。

预计标签文件将用于语音调整；例如，文本到语音和语音转换。

目录结构与JSUT完全相同。如果需要，您可以将标签文件放在JSUT数据目录中：

 tree ~/data/jsut_ver1.1/ -d -L 2
/home/ryuichi/data/jsut_ver1.1/
├── basic5000
│   ├── lab
│   └── wav
├── countersuffix26
│   ├── lab
│   └── wav
├── loanword128
│   ├── lab
│   └── wav
├── onomatopee300
│   ├── lab
│   └── wav
├── precedent130
│   ├── lab
│   └── wav
├── repeat500
│   ├── lab
│   └── wav
├── travel1000
│   ├── lab
│   └── wav
├── utparaphrase512
│   ├── lab
│   └── wav
└── voiceactress100
    ├── lab
    └── wav

标签格式

字段： <begin_time> <end_time> <full-context-label> 。时间与HTK标签一样的100N单元。

 $ cat basic5000/lab/BASIC5000_0773.lab | head
 
0 2525000 xx^xx-sil+s=a/A:xx+xx+xx/B:xx-xx_xx/C:xx_xx+xx/D:18+xx_xx/E:xx_xx!xx_xx-xx/F:xx_xx#xx_xx@xx_xx|xx_xx/G:6_3%0_xx_xx/H:xx_xx/I:xx-xx@xx+xx&xx-xx|xx+xx/J:1_6/K:3+6-32
2525000 3825000 xx^sil-s+a=N/A:-2+1+6/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
3825000 4825000 sil^s-a+N=g/A:-2+1+6/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
4825000 5825000 s^a-N+g=i/A:-1+2+5/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
5825000 6125000 a^N-g+i=i/A:0+3+4/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
6125000 7524999 N^g-i+i=N/A:0+3+4/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
7524999 8125000 g^i-i+N=w/A:1+4+3/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
8125000 8425000 i^i-N+w=a/A:2+5+2/B:xx-xx_xx/C:18_xx+xx/D:24+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
8425000 10125000 i^N-w+a=pau/A:3+6+1/B:18-xx_xx/C:24_xx+xx/D:07+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32
10125000 11325000 N^w-a+pau=d/A:3+6+1/B:18-xx_xx/C:24_xx+xx/D:07+xx_xx/E:xx_xx!xx_xx-xx/F:6_3#0_xx@1_1|1_6/G:3_1%0_xx_0/H:xx_xx/I:1-6@1+3&1-6|1+32/J:2_10/K:3+6-32

有关详细信息，请参阅hts文档：http：//hts.sp.nitech.ac.jp

我该怎么办？

如果您想制作传统的基于DNN的TTS系统，请通过https://r9y9.github.io/nnmnkwii/latest/查看教程。您可以使用对齐方式和全文标签来生成语言特征。

如果您以端到端的方法为条，请查看https://github.com/espnet/espnet。标签在JSUT食谱的预处理阶段使用（另请参见https://r9y9.github.io/blog/2017/11/11/12/jsut_ver1/知道为什么我们需要端到端端TTS的标签）。

演讲happy hacking！

源代码生成标签

https://github.com/r9y9/segentation-kit/tree/jsut3

注意

• 一致性可能会犯错，因为它们是由朱利叶斯自动生成的。请注意，它们不是手工注销的标签。

参考

• JSUT（东京大学的日本演讲语料库）
• HTS
• 朱利叶斯
• OpenJtalk
• 日本语端到端音声合成に使えるコーパスjsutの前处理[arxiv：1711.00354]
• Pyopenjtalk
• nnmnkwii
• Saruwatari-lab手工宣传的语音和韵律信息。