VTLN Through Frequency Warping Based on Pitch<br />10.14209/jcis.2003.10

Abstract

This article describes a Vocal Tract Length Normalization (VTLN) procedure through frequency warping based on pitch estimates. This procedure aims to reduce the inter-speaker variability of speech signals in order to obtain a robust automatic speech recognition system. Two additional methods are also described: one for reducing the environment variability and another for compensating the coarticulation effects on connected word pronunciation. Environment variability is compensated by explicitly modeling some frequent noise phenomena. Coarticulation phenomena compensation reduces speech signal variability by modeling events that result from coarticulation between adjacent models. Inter-speaker variability removal is performed by a traditional speaker normalization method, which consists in expanding or compressing the Mel filterbank bandwidths, in order to normalize the Vocal Tract Length (VTL) of each speaker. Most of the existing methods for VTL estimation are based on formant estimation, but the difficulty of formant estimation is a known performance limitation. The proposed method overcomes such a problem since it estimates the warping factor through pitch. The recognition results, obtained for a telephone digit recognition task (with phones and sub words as units), prove that this procedure leads to similar improvements to those obtained with traditional methods based on formant estimates, actually outperforming them in some situations.