发明名称 |
FAST, LANGUAGE-INDEPENDENT METHOD FOR USER AUTHENTICATION BY VOICE |
摘要 |
A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker-specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated. |
申请公布号 |
US2014195237(A1) |
申请公布日期 |
2014.07.10 |
申请号 |
US201414151605 |
申请日期 |
2014.01.09 |
申请人 |
BELLEGARDA Jerome R.;SILVERMAN Kim E. A. |
发明人 |
BELLEGARDA Jerome R.;SILVERMAN Kim E. A. |
分类号 |
G10L15/07 |
主分类号 |
G10L15/07 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
Saratoga CA US |