Speaker adaptation using combined transformation and Bayesian methods
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 680-683
- https://doi.org/10.1109/icassp.1995.479785
Abstract
The performance and robustness of a speech recognition system can be improved by adapting the speech models to the speaker, the channel and the task. In continuous mixture-density hidden Markov models the number of component densities is typically very large, and it may not be feasible to acquire a large amount of adaptation data for robust maximum-likelihood estimates. To solve this problem, we propose a constrained estimation technique for Gaussian mixture densities, and combine it with Bayesian techniques to improve its asymptotic properties. We evaluate our algorithms on the large-vocabulary Wall Street Journal corpus for nonnative speakers of American English. The recognition error rate is comparable to the speaker-independent accuracy achieved for native speakers.Keywords
This publication has 9 references indexed in Scilit:
- A comparative study of spectral mapping for speaker adaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Stochastic matching for robust speech recognitionIEEE Signal Processing Letters, 1994
- 1993 benchmark tests for the ARPA spoken language programPublished by Association for Computational Linguistics (ACL) ,1994
- On speaker-independent, speaker-dependent, and speaker-adaptive speech recognitionIEEE Transactions on Speech and Audio Processing, 1993
- Speaker adaptation based on MAP estimation of HMM parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- The design for the wall street journal-based CSR corpusPublished by Association for Computational Linguistics (ACL) ,1992
- Robust speaker adaptation using a piecewise linear acoustic mappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- A study on speaker adaptation of the parameters of continuous density hidden Markov modelsIEEE Transactions on Signal Processing, 1991