๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Speaker adaptation techniques for speech recognition using probabilistic models

โœ Scribed by Koichi Shinoda

Publisher
John Wiley and Sons
Year
2005
Tongue
English
Weight
353 KB
Volume
88
Category
Article
ISSN
1042-0967

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

N-Best-based unsupervised speaker adapta
N-Best-based unsupervised speaker adaptation for speech recognition
โœ Tomoko Matsui; Sadaoki Furui ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 251 KB

This paper proposes an instantaneous speaker adaptation method that uses N-best decoding for continuous mixture-density hidden-Markovmodel-based speech-recognition systems. This method is effective even for speakers whose decoding using speaker-independent (SI) models are error-prone and for whom sp

Automatic selection of phonetically dist
Automatic selection of phonetically distributed sentence sets for speaker adaptation with application to large vocabulary Mandarin speech recognition
โœ Jia-lin Shen; Hsin-min Wang; Ren-yuan Lyu; Lin-shan Lee ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 163 KB

This paper presents an approach of automatic selection of phonetically distributed sentence sets for speaker adaptation, and applies the concept to the task of Mandarin speech recognition with very large vocabulary. This is a different approach to the adaptation data selection problem. A computer al

Combined Bayesian and predictive techniq
Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models
โœ SM Ahadi; PC Woodland ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 302 KB

One problem faced by some model adaptation techniques is that only the parameters of those models which are observed in the adaptation data are updated. Hence, with small amounts of adaptation data most of the system parameters remain unchanged. In this paper, a technique called regression-based mod