Fast speaker adaptation for speech recognition systems

International Conference on Acoustics, Speech, and Signal ProcessingPublished 4 December 2002

Fritz Class, A. Kaltenmeier, P. Regel, K. Trottler

DOI10.1109/icassp.1990.115556

Citations29

TL;DR

Different speaker adaptation methods for speech recognition systems adapting automatically to new and unknown speakers in a short training phase are discussed, and the results show that in both systems speaker-adaptive error rates are close to speaker-dependent error rates.

Abstract

Different speaker adaptation methods for speech recognition systems adapting automatically to new and unknown speakers in a short training phase are discussed. The adaptation techniques aim at transformations of feature vectors, optimized with respect to some constraints. Two different adaptation strategies are discussed. The first one is based on least mean-squared-error optimization. The second method is a codebook-driven feature transformation. Both adaptation techniques are incorporated into two different recognition systems: dynamic time warping (DTW) and hidden Markov modeling (HMM). The results show that in both systems speaker-adaptive error rates are close to speaker-dependent error rates. In the best case the mean error rate of four test speakers decreases by a factor of six compared to the interspeaker error rate without adaptation. A hardware realization of the speaker-adaptive HMM-recognizer is described.>

Keywords

Computer Science

Speaker adaptation through vector quantization

96 Citations2005Kiyohiro Shikano, Kai-Fu Lee +1 more

Vector quantization (VQ) is a technique that reduces the computation amount and memory size drastically and is proposed in order to improve speaker-independent recognition.

Spectral transformations through canonical correlation analysis for speaker adptation in ASR

22 Citations2005Khalid Choukri, Gérard Chollet +1 more

This paper describes a technique of spectral transformation for improved adaptation of a knowledge data base or reference templates to new speakers in automatic speech recognition (ASR).

International Conference on Acoustics, Speech, and Signal ProcessingIterative normalization for speaker-adaptive training in continuous speech recognition

18 Citations2003M.-W. Feng, Richard Schwartz +2 more

The authors present several techniques to improve an algorithm presented last year for speaker-adaptive training in continuous speech recognition, focusing on improving the previous method in the modeling of the spectral differences between two speakers, and the accuracy of the alignment.

Speaker adaptation method for HMM-based speech recognition

17 Citations2003Masafumi Nishimura, Kohei Sugawara

The authors describe a speaker adaptation method consisting of two stages, in the first stage, label prototypes, which represent spectral features, are modified to reduce the total distortion error of vector quantization for a new speaker.

Vector quantization for speaker adaptation

11 Citations2005H Bonneau, J.-L. Gauvain

Comparison of performance of the two methods shows that a new speaker's codebook is not necessary to represent the new speaker, and a vector quantization approach to speaker adaptation is evaluated.

Speaker adaptation for recognition systems with a large vocabulary

4 Citations2003Fritz Class, P. Regel +1 more

It is shown that, by means of adaptation procedures based on statistical correlation analysis, error rates as low as those of a speaker-dependent recognition system can be achieved after an extremely short training phase with any new speaker.