A novel feature transformation for vocal tract length normalization in automatic speech recognition

This paper proposes a method to transform acoustic models that have been trained with a certain group of speakers for use on different speech in hidden Markov model based (HMM-based) automatic speech recognition. Features are transformed on the basis of assumptions regarding the difference in vocal...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on speech and audio processing 1998-11, Vol.6 (6), p.549-557
Main Authors: Claes, T., Dologlou, I., ten Bosch, L., van Compernolle, D.
Format: Article
Language:English
Subjects:
Acoustic testing
Applied sciences
Automatic speech recognition
Cepstral analysis
Error analysis
Exact sciences and technology
Filters
Hidden Markov models
Information, signal and communications theory
Linear approximation
Loudspeakers
Mel frequency cepstral coefficient
Signal processing
Speech processing
Telecommunications and information theory
Vectors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a method to transform acoustic models that have been trained with a certain group of speakers for use on different speech in hidden Markov model based (HMM-based) automatic speech recognition. Features are transformed on the basis of assumptions regarding the difference in vocal tract length between the groups of speakers. First, the vocal tract length (VTL) of these groups has been estimated based on the average third formant F/sub 3/. Second, the linear acoustic theory of speech production has been applied to warp the spectral characteristics of the existing models so as to match the incoming speech. The mapping is composed of subsequent nonlinear submappings. By locally linearizing it and comparing results in the output, a linear approximation for the exact mapping was obtained which is accurate as long as the warping is reasonably small. The feature vector, which is computed from a speech frame, consists of the mel scale cepstral coefficients (MFCC) along with delta and delta/sup 2/-cepstra as well as delta and delta/sup 2/ energy. The method has been tested for TI digits data base, containing adult and children speech, consisting of isolated digits and digit strings of different length. The word error rate when trained on adults and tested on children with transformed adult models is decreased by more than a factor of two compared to the nontransformed case.
ISSN:1063-6676
1558-2353
DOI:10.1109/89.725321