Vector-field-smoothed Bayesian learning for incremental speaker adaptation
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 696-699
- https://doi.org/10.1109/icassp.1995.479789
Abstract
The paper presents a fast and incremental speaker adaptation method called MAP/VFS, which combines maximum a posteriori (MAP) estimation, or in other words Bayesian learning, with vector field smoothing (VFS). The point is that MAP is an intra-class training scheme while VFS is an inter-class smoothing technique. This is a basic technique for on-line adaptation which will be important in constructing a practical speech recognition system. Speaker adaptation speed of the incremental MAP is experimentally shown to be significantly accelerated by the use of VFS in word-by-word adaptation. The recognition performance of MAP is consistently improved and stabilized by VFS. The word error reduction rate achieved in incrementally adapting a few words of sample data is about 22%.Keywords
This publication has 7 references indexed in Scilit:
- Fast telephone channel adaptation based on vector field smoothing techniquePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Four-level tied-structure for efficient representation of acoustic modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Vector-field-smoothed Bayesian learning for fast and incremental speaker/telephone-channel adaptationComputer Speech & Language, 1997
- A study of on-line Bayesian adaptation for HMM-based speech recognitionPublished by International Speech Communication Association ,1993
- Speaker adaptation based on MAP estimation of HMM parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- A study on speaker adaptation of the parameters of continuous density hidden Markov modelsIEEE Transactions on Signal Processing, 1991
- Bayesian learning of Gaussian mixture densities for hidden Markov modelsPublished by Association for Computational Linguistics (ACL) ,1991