학술논문
A frequency warping approach to speaker normalization
Document Type
Periodical
Source
IEEE Transactions on Speech and Audio Processing IEEE Trans. Speech Audio Process. Speech and Audio Processing, IEEE Transactions on. 6(1):49-60 Jan, 1998
Subject
Language
ISSN
1063-6676
1558-2353
1558-2353
Abstract
In an effort to reduce the degradation in speech recognition performance caused by variation in vocal tract shape among speakers, a frequency warping approach to speaker normalization is investigated. A set of low complexity, maximum likelihood based frequency warping procedures have been applied to speaker normalization for a telephone based connected digit recognition task. This paper presents an efficient means for estimating a linear frequency warping factor and a simple mechanism for implementing frequency warping by modifying the filterbank in mel-frequency cepstrum feature analysis. An experimental study comparing these techniques to other well-known techniques for reducing variability is described. The results have shown that frequency warping is consistently able to reduce word error rate by 20% even for very short utterances.