Yu, K and Gales, MJE (2005) Bayesian adaptation and adaptively trained systems. Proceedings of ASRU 2005: 2005 IEEE Automatic Speech Recognition and Understanding Workshop, 2005. pp. 372-377.Full text not available from this repository.
As the use of found data increases, more systems are being built using adaptive training. Here transforms are used to represent unwanted acoustic variability, e.g. speaker and acoustic environment changes, allowing a canonical model that models only the "pure" variability of speech to be trained. Adaptive training may be described within a Bayesian framework. By using complexity control approaches to ensure robust parameter estimates, the standard point estimate adaptive training can be justified within this Bayesian framework. However during recognition there is usually no control over the amount of data available. It is therefore preferable to be able to use a full Bayesian approach to applying transforms during recognition rather than the standard point estimates. This paper discusses various approximations to Bayesian approaches including a new variational Bayes approximation. The application of these approaches to state-of-the-art adaptively trained systems using both CAT and MLLR transforms is then described and evaluated on a large vocabulary speech recognition task. © 2005 IEEE.
|Divisions:||Div F > Machine Intelligence|
|Depositing User:||Cron Job|
|Date Deposited:||07 Mar 2014 12:35|
|Last Modified:||22 Dec 2014 01:17|