Title :
Minimum Bayes risk discriminative language models for Arabic speech recognition
Author :
Hong-Kwang Jeff Kuo;Ebru Arisoy;Lidia Mangu;George Saon
Author_Institution :
IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, U. S. A.
Abstract :
In this paper we explore discriminative language modeling (DLM) on highly optimized state-of-the-art large vocabulary Arabic broadcast speech recognition systems used for the Phase 5 DARPA GALE Evaluation. In particular, we study in detail a minimum Bayes risk (MBR) criterion for DLM. MBR training outperforms perceptron training. Interestingly, we found that our DLMs generalized to mismatched conditions, such as using a different acoustic model during testing. We also examine the interesting problem of unsupervised DLM training using a Bayes risk metric as a surrogate for word error rate (WER). In some experiments, we were able to obtain about half of the gain of the supervised DLM.
Keywords :
"Training","Acoustics","Feature extraction","Training data","Speech recognition","Vectors","Parameter estimation"
Conference_Titel :
Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on
Print_ISBN :
978-1-4673-0365-1
DOI :
10.1109/ASRU.2011.6163932