发明名称 |
METHOD AND SYSTEM FOR REAL-TIME SPEECH RECOGNITION |
摘要 |
Method and system for real-time speech recognition is provided. The speech algorithm runs on a platform having an input-output processor and a plurality of processor units. The processor units operate substantially in parallel or sequentially to perform feature extraction and pattern matching. While th e input-output processor creates a frame, the processor units execute the feature extraction and the pattern matching. Shared memory is provided for supportin g the parallel operation.
|
申请公布号 |
CA2409488(C) |
申请公布日期 |
2007.05.29 |
申请号 |
CA20022409488 |
申请日期 |
2002.10.22 |
申请人 |
DSPFACTORY LTD. |
发明人 |
SHEIKHZADEH-NADJAR, HAMID;CORNU, ETIENNE;DUFAUX, ALAIN;BRENNAN, ROBERT;DESTREZ, NICOLAS |
分类号 |
G10L15/02;G10L15/28 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|