Dominique Salden
08-04-2008 10:36

A Frequency Warping Approach to Speaker Normalization



Li Lee, Richard Rose


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 wellknown 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.