10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Generalized Discriminative Feature Transformation for Speech Recognition

Roger Hsiao, Tanja Schultz

Carnegie Mellon University, USA

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.

Full Paper

Bibliographic reference.  Hsiao, Roger / Schultz, Tanja (2009): "Generalized discriminative feature transformation for speech recognition", In INTERSPEECH-2009, 664-667.