A study on speaker adaptation of the parameters of continuous density hidden Markov models
- 1 April 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 39 (4) , 806-814
- https://doi.org/10.1109/78.80902
Abstract
For a speech-recognition system based on continuous-density hidden Markov models (CDHMM), speaker adaptation of the parameters of CDHMM is formulated as a Bayesian learning procedure. A speaker adaptation procedure which is easily integrated into the segmental k-means training procedure for obtaining adaptive estimates of the CDHMM parameters is presented. Some results for adapting both the mean and the diagonal covariance matrix of the Gaussian state observation densities of a CDHMM are reported. The results from tests on a 39-word English alpha-digit vocabulary in isolated word mode indicate that the speaker adaptation procedure achieves the same level of performance as that of a speaker-independent system, when one training token from each word is used to perform speaker adaptation. It shows that much better performance is achieved when two or more training tokens are used for speaker adaptation. When compared with the speaker-dependent system, it is found that the performance of speaker adaptation is always equal to or better than that of speaker-dependent training using the same amount of training data.Keywords
This publication has 14 references indexed in Scilit:
- Rapid speaker adaptation using a probabilistic spectral mappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multi-style training for robust isolated-word speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Bayesian adaptation in speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Unsupervised speaker adaptation method based on hierarchical spectral clusteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Improved training procedures for hidden Markov modelsThe Journal of the Acoustical Society of America, 1988
- On the use of instantaneous and transitional spectral information in speaker recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Some performance benchmarks for isolated work speech recognition systemsComputer Speech & Language, 1987
- On the use of bandpass liftering in speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- An introduction to hidden Markov modelsIEEE ASSP Magazine, 1986
- Maximum-Likelihood Estimation for Mixture Multivariate Stochastic Observations of Markov ChainsAT&T Technical Journal, 1985