发明名称 |
NEURAL NETWORKS FOR DETECTION OF PHONETIC FEATURES |
摘要 |
In various embodiments, techniques for detecting phonetic features in a stream of speech data are provided by first dividing the stream speech data into a plurality of critical bands, segmenting the critical bands into streams of consecutive windows and determining various parameters for each window per critical band. The various parameters can then be combined using various operators in a multi-layered network including a first layer that can process the various parameters by using a sigmoid operator on a weighted parameters sum. The processed sums can then be further combined using a hierachy of conjonctive and disjunctive operators to produce a stream of detected features.
|
申请公布号 |
WO0131628(A3) |
申请公布日期 |
2001.12.06 |
申请号 |
WO2000US41649 |
申请日期 |
2000.10.27 |
申请人 |
AT & T CORP. |
发明人 |
ALLEN, JONATHAN, B.;RAHIM, MAZIN, G.;SAUL, LAWRENCE, K. |
分类号 |
G10L15/02;G10L15/16;(IPC1-7):G10L15/16 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|