发明名称 |
METHOD FOR AUTOMATIC SPEAKER RECOGNITION |
摘要 |
<p>It is proposed a text-independent automatic speaker recognition (ASkR) system which employs a new speech feature and a new classifier. The statistical feature pH is a vector of Hurst parameters obtained by applying a wavwlet-based multi-dimensional estimator (M dim wavelets) to the windowed short-time segments of speech. The proposed classifier for the speaker identification and verification tasks is based on the multi-dimentional fBm (fractional Brownian motion) model, denoted by M dim fBm. For a given sequence of input speech features, the speaker model is obtained from the sequence of vectors of H parameters, means and variances of these features.</p> |
申请公布号 |
WO2006024117(A1) |
申请公布日期 |
2006.03.09 |
申请号 |
WO2004BR00164 |
申请日期 |
2004.09.02 |
申请人 |
COELHO, ROSANGELA FERNANDES |
发明人 |
COELHO, ROSANGELA FERNANDES |
分类号 |
(IPC1-7):G10L17/00 |
主分类号 |
(IPC1-7):G10L17/00 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|