Factor analyzed HMM topology for speech recognition

Chuan Wei Ting*, Jen-Tzung Chien

*此作品的通信作者

研究成果: Conference article同行評審

摘要

This paper presents a new factor analyzed (FA) similarity measure between two Gaussian mixture models (GMMs). An adaptive hidden Markov model (HMM) topology is built to compensate the pronunciation variations in speech recognition. Our idea aims to evaluate whether the variation of a HMM state from new speech data is significant or not and judge if a new state should be generated in the models. Due to the effectiveness of FA data analysis, we measure the GMM similarity by estimating the common factors and specific factors embedded in the HMM means and variances. Similar Gaussian densities are represented by the common factors. Specific factors express the residual of similarity measure. We perform a composite hypothesis test due to common factors as well as specific factors. An adaptive HMM topology is accordingly established from continuous collection of training utterances. Experiments show that the proposed FA measure outperforms other measures with comparable size of parameters.

原文English
頁(從 - 到)1415-1418
頁數4
期刊Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
出版狀態Published - 26 十一月 2009
事件10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom
持續時間: 6 九月 200910 九月 2009

指紋

深入研究「Factor analyzed HMM topology for speech recognition」主題。共同形成了獨特的指紋。

引用此