发明名称 |
Speech recognition |
摘要 |
A speech waveform to be modelled is represented by a set of feature extracted parameters in the time domain individual ones of one or more of the feature extracted parameters are divided to provide a plurality of frequency channels, and at least one of the frequency channels is demodulated to provide at least one corresponding baseband frequency signal.
|
申请公布号 |
GB2355834(A) |
申请公布日期 |
2001.05.02 |
申请号 |
GB19990025676 |
申请日期 |
1999.10.29 |
申请人 |
* NOKIA MOBILE PHONES LIMITED |
发明人 |
JILEI * TIAN;KARI * LAURILA |
分类号 |
G10L15/02;G10L15/28;(IPC1-7):G10L15/02;G10L15/20 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|