发明名称 |
Source normalization training for modeling of speech |
摘要 |
<p>A maximum likelihood (ML) linear regression (LR) solution to environment normalization is provided where the environment is modeled as a hidden (non-observable) variable. By application of an expectation maximization algorithm and extension of Baum-Welch forward and backward variables (Steps 23a-23d) a source normalization is achieved such that it is not necessary to label a database in terms of environment such as speaker identity, channel, microphone and noise type. <IMAGE></p> |
申请公布号 |
EP0913809(A2) |
申请公布日期 |
1999.05.06 |
申请号 |
EP19980202871 |
申请日期 |
1998.08.26 |
申请人 |
TEXAS INSTRUMENTS INCORPORATED |
发明人 |
GONG, YIFAN |
分类号 |
G10L15/065;G10L15/14;(IPC1-7):G10L15/06 |
主分类号 |
G10L15/065 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|