A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition
A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition
复制标题
DOI：
10.1109/chinsl.2004.1409595
复制
发表时间：
2004-12
期刊：
影响因子：
--
通讯作者：
Donglai Zhu;Qiang Huo;Jian Wu
中科院分区：
文献类型：
--
作者：
Donglai Zhu;Qiang Huo;Jian Wu
在我们以前的工作中，切换线性高斯隐马尔可夫模型（SLGHMM）和它的分段衍生物，SSLGHMM，提出了铸造的问题，建模一个嘈杂的语音话语鲁棒自动语音识别设计良好的动态贝叶斯网络。SSLGHMM的一个重要问题是如何指定一个开关状态值的特征向量在一个给定的语音话语的每一帧。在本文中，我们提出了几种方法来解决这个问题，并比较它们在Aurora3连接数字识别任务上的性能。
In our previous works, a switching linear Gaussian hidden Markov model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of the feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks.