发明名称 |
Speech recognition using both time encoding and HMM in parallel |
摘要 |
A speech recognition method that combines time encoding and hidden Markov approaches. The speech is input and encoded using time encoding, such as TESPAR. A hidden Markov model generates scores; the scores are used to determine the speech element; and the result is output.
|
申请公布号 |
US6301562(B1) |
申请公布日期 |
2001.10.09 |
申请号 |
US20000559760 |
申请日期 |
2000.04.27 |
申请人 |
NEW TRANSDUCERS LIMITED |
发明人 |
AZIMA HENRY;FEREKIDIS CHARALAMPOS;KAVANAGH SEAN |
分类号 |
G10L15/02;(IPC1-7):G01L15/00 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|