发明名称 HIGH-ORDER ENTROPY ERROR FUNCTIONS FOR NEURAL CLASSIFIERS
摘要 <p>An automatic speech recognition system comprising a speech decoder to resolve phone and world level information, a vector generator to generate information vectors on which a confidence measure is based by a neural network classifier (ANN). An error signal is designed which is not subject to false saturation or over specialization. The error signal is integrated into an error function which is back propagated through the ANN.</p>
申请公布号 WO2002091355(A1) 申请公布日期 2002.11.14
申请号 CN2001000686 申请日期 2001.05.08
申请人 发明人
分类号 主分类号
代理机构 代理人
主权项
地址