CUED Publications database

Constrained discriminative mapping transforms for unsupervised speaker adaptation

Chen, L and Gales, MJF and Chin, KK (2011) Constrained discriminative mapping transforms for unsupervised speaker adaptation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 5344-5347. ISSN 1520-6149

Full text not available from this repository.


Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs are more robust to unreliable transcriptions than directly estimating adaptation transforms in a discriminative fashion. They were previously proposed for use with MLLR transforms with the associated need to explicitly transform the model parameters. In this work the DMT is extended to CMLLR transforms. As these operate in the feature space, it is only necessary to apply a different linear transform at the front-end rather than modifying the model parameters. This is useful for rapidly changing speakers/environments. The performance of DMTs with CMLLR was evaluated on the WSJ 20k task. Experimental results show that DMTs based on constrained linear transforms yield 3% to 6% relative gain over MLE transforms in unsupervised speaker adaptation. © 2011 IEEE.

Item Type: Article
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:46
Last Modified: 03 Aug 2017 03:15