Proposed in this paper is a method for speaker adaptation, namely, transfer vector field smoothing (VFS) with respect to transfer vector reliability. We also discuss the results obtained in applying the proposed method to MAP-VFS speaker adaptation. The transfer vectors are maximum a posteriori prob
Speaker adaptation of acoustic models using correlations of training transfer vectors
โ Scribed by Satoshi Takahashi; Shigeki Sagayama
- Publisher
- John Wiley and Sons
- Year
- 2000
- Tongue
- English
- Weight
- 203 KB
- Volume
- 31
- Category
- Article
- ISSN
- 0882-1666
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
The point sound source model calculating the transfer matrix of thin acoustic cavities has been extensively utilized in analyzing certain mufflers. However, the computational result of the transfer matrix is not valid due to the singularity of the point source model. In this paper, a surface source
## Abstract ## Background The pig lung, given its gross anatomical, histological and physiological similarities to the human lung, may be useful as a large animal model, in addition to rodents, in which to assess the potential of vectors for pulmonary airway gene transfer. The aim of this study wa