发明名称 |
Audio-visual feature fusion and support vector machine useful for continuous speech recognition |
摘要 |
A speech recognition method includes several embodiments describing application of support vector machine analysis to a mouth region. Lip position can be accurately determined and used in conjunction with synchronous or asynchronous audio data to enhance speech recognition probabilities.
|
申请公布号 |
US7472063(B2) |
申请公布日期 |
2008.12.30 |
申请号 |
US20020326368 |
申请日期 |
2002.12.19 |
申请人 |
INTEL CORPORATION |
发明人 |
NEFIAN ARA V.;PI XIAOBO;LIANG LUHONG;LIU XIAOXING;ZHAO YIBAO |
分类号 |
G10L15/14;G06K9/62;G06K9/68;G06K9/70;G10L15/24 |
主分类号 |
G10L15/14 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|