GMM-HMM ACOUSTIC MODEL TRAINING BY A TWO LEVEL PROCEDURE WITH GAUSSIAN COMPONENTS DETERMINED BY AUTOMATIC MODEL SELECTION | |
Su, Dan ; Wu, Xihong ; Xu, Lei | |
2010 | |
关键词 | speech recognition model selection Bayesian Ying-Yang learning GMMs HMMs SPEECH RECOGNITION |
英文摘要 | This paper investigates the Bayesian Ying-Yang (BYY) learning for speech recognition via Gaussian mixture models (GMMs) based Hidden Markov models (HMMs). A two level procedure is proposed with the hidden Markov level trained still under the maximum likelihood principle by the Baum-Welch algorithm but with the GMMs level trained under the BYY best harmony. We proposed a new batch way EM-like Ying-Yang alternation algorithm and used it as a plug-in block to the Baum-Welch algorithm. The advantage is that number of GMM components can be automatically determined during this BYY harmony learning and that the resulted model parameters become less affected than EM-ML training by the problem of overfitting and singular solution. In comparison with the standard EM-ML training and classical model selection criterions, including BIC and AIC, speech recognition experiments in a large vocabulary task on the Hub4 broadcast news database shown that the proposed algorithm provides an improved performance and also good convergence.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000287096004201&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Acoustics; Computer Science, Theory & Methods; Engineering, Electrical & Electronic; CPCI-S(ISTP); 1 |
语种 | 英语 |
DOI标识 | 10.1109/ICASSP.2010.5495122 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/292983] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Su, Dan,Wu, Xihong,Xu, Lei. GMM-HMM ACOUSTIC MODEL TRAINING BY A TWO LEVEL PROCEDURE WITH GAUSSIAN COMPONENTS DETERMINED BY AUTOMATIC MODEL SELECTION. 2010-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论