Multiple Application of the MLLT Based on Clustering Supported by Phonetic Knowledge

摘要：

This paper intends to show the effect of multiple use of a Maximum Likelihood Linear Transform (MLLT) in continuous speech recognition tasks.The correspon-ding covariance matrices that were subjected to the transform were clustered using phonetic knowledge.The impact of this approach was tested on the ASRs with PLP-and MFCC-based front-ends and was compared with other known feature decorrelation and dimension reduction techniques.

作者: J.V.Psutka Ale(s) Pra(z)(a)k

作者单位: Department of Cybernetics,Faculty of Applied Sciences,University of West Bohemia,Pilsen,Czech Republ SpeechTech,Pilsen,Czech Republic

会议类型: 国际会议

会议名称: 9th International Conference on Signal Processing(第九届国际信号处理学术会议)(ICSP08)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-26（万方平台首次上网日期，不代表论文的发表时间）