HTS version 2.1 includes hidden semi-Markov model (HSMM) training/adaptation/synthesis, speech parameter generation algorithm considering global variance (GV), SMAPLR/CSMAPLR adaptation, and other minor new features.

基于隐马尔可夫模型的语音单字识别研究：本文针对线性模型在语音识别中的不足, 进行了隐马尔可夫模型(HMM)在 语音单字识别中的研究,主要对观察输出概率求解、 最佳状态序列寻找、 参数估计和 模型参数的选择进行了探讨.-Based on hidden Markov model speech word recognition: the lack of the linear model in speech recognition, hidden Markov model (HMM) speec

A novel approach to unsupervised stochastic model-based image segmentation is presented and the problems of parameter estimation and image segmentation are formulated as Bayesian learning. In order to draw samples corresponding to di€ erent c