Sciweavers

INTERSPEECH
2010

Discriminative adaptation for log-linear acoustic models

13 years 5 months ago
Discriminative adaptation for log-linear acoustic models
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian models, and a more direct parametrisation of the posterior model. To competitively use log-linear models for speech recognition, important methods, such as speaker adaptation, have to be reformulated in a log-linear framework. In this work, an approach to log-linear affine feature transforms for speaker adaptation is described. Experiments for both supervised and unsupervised adaptation are presented, showing improvements over a maximum likelihood baseline in the form of feature space maximum likelihood linear regression for the case of supervised adaptation.
Jonas Lööf, Ralf Schlüter, Hermann
Added 18 May 2011
Updated 18 May 2011
Type Journal
Year 2010
Where INTERSPEECH
Authors Jonas Lööf, Ralf Schlüter, Hermann Ney
Comments (0)