DMCA
Generalized Discriminative Feature Transformation for Speech Recognition
| Citations: | 5 - 4 self |
BibTeX
@MISC{Hsiao_generalizeddiscriminative,
author = {Roger Hsiao and Tanja Schultz},
title = {Generalized Discriminative Feature Transformation for Speech Recognition},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We propose a new algorithm called Generalized Discriminative Feature Transformation (GDFT) for acoustic models in speech recognition. GDFT is based on Lagrange relaxation on a transformed optimization problem. We show that the existing discriminative feature transformation methods like feature space MMI/MPE (fMMI/MPE), region dependent linear transformation (RDLT), and a non-discriminative feature transformation, constrained maximum likelihood linear regression (CMLLR) are special cases of GDFT. We evaluate the performance of GDFT for Iraqi large vocabulary continuous speech recognition. Index Terms: speech recognition, discriminative training, feature transformation
Keyphrases
speech recognition discriminative feature transformation index term maximum likelihood linear regression transformed optimization problem region dependent linear transformation feature space mmi mpe feature transformation discriminative feature transformation method new algorithm fmmi mpe generalized discriminative feature transformation acoustic model discriminative training lagrange relaxation special case non-discriminative feature transformation
