SUPPORT VECTOR MACHINES FOR SEGMENTAL MINIMUM BAYES RISK DECODING OF CONTINUOUS SPEECH

Download: PDF, slides.

“SUPPORT VECTOR MACHINES FOR SEGMENTAL MINIMUM BAYES RISK DECODING OF CONTINUOUS SPEECH” by V. Venkataramani, S. Chakrabartty, and W. Byrne. In IEEE Automatic Speech Recognition and Understanding Workshop, 2003.

Abstract

Segmental Minimum Bayes Risk (SMBR) Decoding involves the refinement of the search space into manageable confusion sets i.e., smaller sets of confusable words. We describe the application of Support Vector Machines (SVMs) as discriminative models for the refined search space. We show that SVMs, which in their basic formulation are binary classifiers of fixed dimensional observations, can be used for continuous speech recognition. We also study the use of GiniSVMs, which is a variant of the basic SVM. On a small vocabulary task, we show this two pass scheme outperforms MMI trained HMMs. Using system combination we also obtain further improvements over discriminatively trained HMMs.

Download: PDF, slides.

BibTeX entry:

@inproceedings{asru03_svmsmbr,
   author = {V. Venkataramani and S. Chakrabartty and W. Byrne},
   title = {SUPPORT VECTOR MACHINES FOR SEGMENTAL MINIMUM {B}AYES RISK
	DECODING OF CONTINUOUS SPEECH},
   booktitle = {{IEEE} Automatic Speech Recognition and Understanding
	Workshop},
   pages = {(6 pages)},
   year = {2003}
}

Back to Bill Byrne publications.