“Speech book”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
语种识别(嘉威)
 
(6位用户的38个中间修订版本未显示)
第1行: 第1行:
  
 +
==Introduction==
  
 +
'''《语音识别基本法》''' is an introduction book to speech processing. The main part of the book is about speech recognition,
 +
though related topics are involved, including speaker recognition, language recognition and speech synthesis.
  
'''《语音识别基本法》'''
 
  
 +
[https://mp.weixin.qq.com/s/xxQXYqdbcsKIujxydayNxw Paper version] is already published.
  
*[[媒体文件:20181226 speech book.pdf | Version 20181226]]
 
  
*[[媒体文件:20181225 speech book.pdf | Version 20181225]]
+
==Current version==
  
*[[媒体文件:20181224 speech book.pdf | Version 20181224]]
+
*[[媒体文件:speech book.pdf | Version 20201012]]
  
 +
==Tex source==
  
 
+
*[https://gitlab.com/tzyll/speech_book GitLab repository]
=语音识别基础知识(阿汤)=
+
==语音是什么==
+
==语音识别方法==
+
==语音识别工具==
+
 
+
=语音识别基本流程(阿汤)=
+
==语音识别流程速览==
+
==声学特征==
+
==GMM-HMM==
+
==DNN==
+
==解码器==
+
 
+
=语音识别实际问题=
+
==说话人自适应(启明)==
+
[[媒体文件:Spk.pdf|pdf]]
+
 
+
[http://wangd.cslt.org/book/kaldi/spk-adapt.rar latex]
+
 
+
==噪声对抗与环境鲁棒性(启明)==
+
 
+
[[媒体文件:Noise.pdf|pdf]]
+
 
+
[http://wangd.cslt.org/book/kaldi/noise-robust.rar latex]
+
 
+
 
+
==新词处理与领域泛化(文强)==
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ef/New_word_du.pdf pdf]
+
 
+
==小语种识别(石颖)==
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Minority_20190109.pdf pdf]
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/02/Minority_asr.rar LaTex]
+
 
+
==关键词唤醒与嵌入式系统(嘉瑶)==
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf pdf]
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/70/Kws.rar Latex]
+
 
+
=前沿课题=
+
==说话人识别(蓝天)==
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Sre.pdf pdf]
+
 
+
==语种识别(诏娣)==
+
 
+
[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Lid.pdf pdf]
+
 
+
==情绪识别(嘉威)==
+
 
+
==语音合成(启明)==
+

2021年3月15日 (一) 06:46的最后版本

Introduction

《语音识别基本法》 is an introduction book to speech processing. The main part of the book is about speech recognition, though related topics are involved, including speaker recognition, language recognition and speech synthesis.


Paper version is already published.


Current version

Tex source