Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

Download: PDF.

“Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition” by W. Byrne, Google, Inc, Mountain View, CA, USA. Sep. 2005. Talk.

Abstract

Progress in automatic speech recognition is frequently measured by easily computed, task-neutral measures such as Word Error Rate. Ideally it could be possible to design systems tailored for any application no matter how complex or specialized the performance criteria. Minimum Bayes-Risk (MBR) processing is a modeling framework that attempts to minimize the empirical expected risk under task-specific loss functions that describe desired system behavior. This presentation will describe risk-based recognition and model estimation procedures developed for the refinement of automatic speech recognition systems. The MBR formulation has also made it possible to implement a hybrid estimation and discriminative training approach called Acoustic Code-Breaking. This is a divide-and-conquer strategy that breaks continuous speech recognition problems into a sequence of smaller, distinct subproblems that can be solved independently using specially trained discriminative models such as Support Vector Machines. These estimation and decoding approaches will be described, along with evaluation of their performance on various automatic speech recognition tasks.

Download: PDF.

BibTeX entry:

@misc{googl05minrisk,
   author = {W. Byrne},
   title = {Minimum {B}ayes Risk Estimation and Decoding in Large
	Vocabulary Continuous Speech Recognition},
   publisher = {Google, Inc, Mountain View, CA, USA},
   month = sep,
   year = {2005},
   note = {Talk}
}

Back to Bill Byrne publications.