发明名称 |
GMM INCREMENTAL ROBUST ADAPTATION WITH FORGETTING FACTOR FOR SPEAKER VERIFICATION |
摘要 |
Speaker recognition system uses a speaker model adaptation method with small amounts of data in order to obtain a good performance. However, in a conventional adaptation method, when new data has an outlier such as a noise or an utterance change, which results in inaccurate speaker model. As time goes by, a rate in which new data are adapted to a model is reduced. A new method uses an incremental robust adaptation in order to reduce effect of outlier and uses forgetting factor in order to maintain adaptive rate of new data. |
申请公布号 |
WO2004112001(A1) |
申请公布日期 |
2004.12.23 |
申请号 |
WO2003KR01207 |
申请日期 |
2003.06.19 |
申请人 |
KWANGWOON FOUNDATION;LEE, KI YONG;LEE, JONG JOO;LEE, YOUN JEONG |
发明人 |
LEE, KI YONG;LEE, JONG JOO;LEE, YOUN JEONG |
分类号 |
G10L17/04 |
主分类号 |
G10L17/04 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|