Acoustic adaptation using nonlinear transformations of HMM parameters
- 24 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15206149) , 729-732
- https://doi.org/10.1109/icassp.1996.543224
Abstract
Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. We extend this approach to use nonlinear transformations. These are implemented by multilayer perceptrons (MLPs) which transform the Gaussian means. We derive a generalized expectation-maximization (GEM) training algorithm to estimate the MLP weights. Some preliminary experimental results on nonnative speaker adaptation are presented.Keywords
This publication has 7 references indexed in Scilit:
- Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker adaptation using combined transformation and Bayesian methodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A maximum-likelihood approach to stochastic matching for robust speech recognitionIEEE Transactions on Speech and Audio Processing, 1996
- A comparative study of speaker adaptation techniquesPublished by International Speech Communication Association ,1995
- Speaker adaptation using constrained estimation of Gaussian mixturesIEEE Transactions on Speech and Audio Processing, 1995
- The hub and spoke paradigm for CSR evaluationPublished by Association for Computational Linguistics (ACL) ,1994
- Speaker adaptation based on MAP estimation of HMM parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993