In encoding feature compensation, the MAP (Maximum A Posterior) method and the ML (Maximum Likelihood) method are applied to the speaker recognition systems.
在编码特征补偿方面,将两种语音识别中的编码补偿方法,最大后验概率MAP(Maximum A Posterior)方法和最大似然估计ML(Maximum Likelihood)方法,应用到说话人识别系统当中。
参考来源 - 说话人识别中不同语音编码影响的补偿方法·2,447,543篇论文数据,部分数据来源于NoteExpress
特征补偿是一种常用的鲁棒性识别技术。
A common technique for robust speech recognition is feature compensation.
本文提出了一种基于概率模型的特征补偿算法。
The article introduces a new feature compensation method which based probability model in detail.
在概率模型中,给出了引入倒谱预测值的动态相关性来进行特征补偿的方法。
The paper introduces a new feature compensation method which will induct the relativity of the prediction of spectrum based probability model in detail.
应用推荐