发明名称 |
Factorial hidden markov model for audiovisual speech recognition |
摘要 |
A speech recognition method includes use of synchronous or asynchronous audio and a video data to enhance speech recognition probabilities. A two stream factorial hidden Markov model is trained and used to identify speech. At least one stream is derived from audio data and a second stream is derived from mouth pattern data. Gestural or other suitable data streams can optionally be combined to reduce speech recognition error rates in noisy environments.
|
申请公布号 |
US2003212556(A1) |
申请公布日期 |
2003.11.13 |
申请号 |
US20020142447 |
申请日期 |
2002.05.09 |
申请人 |
NEFIAN ARA V. |
发明人 |
NEFIAN ARA V. |
分类号 |
G06K9/00;G06K9/62;G10L15/14;G10L15/24;(IPC1-7):G10L15/14 |
主分类号 |
G06K9/00 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|