Vector-field-smoothed Bayesian learning for fast and incremental speaker/telephone-channel adaptation
✍ Scribed by Jun-ichi Takahashi; Shigeki Sagayama
- Publisher
- Elsevier Science
- Year
- 1997
- Tongue
- English
- Weight
- 366 KB
- Volume
- 11
- Category
- Article
- ISSN
- 0885-2308
No coin nor oath required. For personal study only.
✦ Synopsis
This paper describes an on-line adaptation method that combines maximum a posteriori (MAP) estimation for intra-class training (the training scheme incorporates new training samples with prior information) with vector field smoothing (VFS) for inter-class smoothing. Results of experiments comparing recognition performance of MAP/VFS with MAP adaptation for speaker adaptation and simultaneous adaptation of speaker and telephone channel show that fast and incremental adaptation can be achieved even with a relatively small number of training samples (under 10 words) due to VFS's ability to consistently enhance MAP adaptation. High word error reduction rates, which in the experiments were 22% for speaker adaptation in a large-vocabulary isolated-word recognition task (vocabulary size=2575) and 48% for simultaneous adaptation of speaker and telephone channel in a 100-isolated-word recognition task, can be achieved through word-by-word incremental adaptation using 10-word data.