The following description describes the basic features of the voice recognition mechanism which is based on a speaker dependent is dated word recognition method.
下列叙述说明了以与授话人有关的分离词汇识别法为基础的语音识别机理的基本特点。
Using different feature vectors, the effect of the vocoders differs on speaker dependent continuous speech recognition and speaker independent connected digits recognition.
对于特定人连续语音识别系统和非特定人连接词识别系统，在使用不同的特征矢量时，不同编码器产生的识别效果有比较大的差异。
For speaker identification, Expectation Maximization Algorithm (EM) is adopted to train speaker dependent model, and afterwards recognize speaker according to Maximum a Posteriori Criterion (MAP).
对于语者辨识，语者特定模型直接用语者的语料借助于期望值最大化算法（EM）来训练，辨识算法采用了最大事后概率法则（MAP）；
应用推荐