发明名称 |
Method of generating a subword model for speech recognition |
摘要 |
An automated method of generating a subword model for speech recognition dependent on phoneme context for processing speech information using a Hidden Markov Model in which static features of speech and dynamic features of speech are modeled as a chain of a plurality of output probability density distributions. The method comprising determining a phoneme context class which is a model unit allocated to each model, the number of states used for representing each model, relationship of sharing of states among a plurality of models, and output probability density distribution of each model, by repeating splitting of a small number of states, provided in an initial Hidden Markov Model, based on a prescribed criterion on a probabilistic model.
|
申请公布号 |
US5677988(A) |
申请公布日期 |
1997.10.14 |
申请号 |
US19950532318 |
申请日期 |
1995.09.21 |
申请人 |
ATR INTERPRETING TELEPHONY RESEARCH LABORATORIES |
发明人 |
TAKAMI, JUN-ICHI;SAGAYAMA, SHIGEKI |
分类号 |
G10L15/06;G10L15/02;G10L15/14;(IPC1-7):G10L5/06 |
主分类号 |
G10L15/06 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|