Speaker normalization using efficient frequency warping procedures
- 24 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 353-356vol.1
- https://doi.org/10.1109/icassp.1996.541105
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 filter-bank in mel-frequency cepstrum feature analysis. An experimental study comparing these techniques to other well-known techniques for reducing variability is described. The results showed that frequency warping was consistently able to reduce word error rate by 20% even for very short utterancesKeywords
This publication has 1 reference indexed in Scilit:
- A feature-space transformation for telephone based speech recognitionPublished by International Speech Communication Association ,1995