A STUDY ON YUNNAN DIALECTAL CHINESE SPEECH RECOGNITION
In this paper, a Yunnan dialectal accents Putonghua speech carpus which collected by our lab is used in Yunnan dialectal Chinese speech recognition study. Several acoustic adaptation techniques are preformed to improve the recognition rate for accented speech and their performances are compared. Firstly, the baseline system is trained using the project 863 standard Putonghua corpus, the recognition rate of Yunnan dialectal accents speech is obtained. It is lower than the recognition rate of standard Putonghua speech. Secondly, based on the Yunnan dialectal accents Putonghua speech corpus, Yunnan dialectal accents acoustic models are built, their performances are tested. Finally, speaker adaptation experiments are implemented. MLLR and MAP adaptation methods are used. The results show the proposed methods can evidently improve the recognition performances for Yunnan dialectal accents.
Putonghua speech recognition Dialectal accent Acoustical adaptation MLLR MAP
YUAN-YUAN PU JIAN YANG HONG WEI DAN XU
School of Information , Yunnan University, Kunming 650091, China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2760-2764
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）