Built-in speech discriminating method based on sub-word hidden Markov model
Title：
Built-in speech discriminating method based on sub-word hidden Markov model
Application Number：
 200710064951
Application Date：
 2007/03/30
Announcement Date：
 2007/09/05
Pub. Date：
Publication Number：
 101030369
Announcement Number：
Grant Date：
Granted Pub. Date：
ApplicationType：
 Invention
State/Country：
 11[China|beijing]
IPC：
 G10L 15/14
Applicant(s)：
 Tsinghua Univ.
Inventor(s)：
 Liang Weiqian, Dong Ming, Ding Yuguo, Liu Runsheng
Key Words：
 Built-in, speech discriminating, sub-word hidden Markov model
Abstract：
 An embedded voice identifying method based on sub-word hidden Markov model includes detecting end point, picking up frame synchronous acoustic characters, calculating acoustic character vector sequence used on identification network-decoding and decoding by identification network. The device used for realizing said method is also disclosed.
Claim：
Priority：
PCT：
LegalStatus：

Recommend this patent:
1 2 3 4 5
Average ( 0 votes):
                                                                          Recommended Patents>>

Relevancy information



Other Patents of Same Inventor

Zero zone destruction and mixed working medium suitable for compression type heat pump
Mixed heat pump work substance with zero ozone layer destroying potential
Coprocessor



News & Events More>>

Last Update  
2008-4-17
  Selected patents owned by Tsinghua University filed in 2005 are loaded.
2008-3-31
  Selected patents owned by Tsinghua University filed in 2006 and 2007 are load.







Copyright 2008-2015 All Rights Reserved Patent License of China.      Designed by Easygo