Skip Navigation

IEICE Transactions on Information and Systems 2007 E90-D(5):835-843; doi:10.1093/ietisy/e90-d.5.835
This Article
Right arrow Full Text (PDF)
Right arrow References
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrow Request Permissions
Google Scholar
Right arrow Articles by KOBAYASHI, A.
Right arrow Articles by IMAI, T.
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

Copyright © 2007 The Institute of Electronics, Information and Communication Engineers

Regular Section -- Papers -- Speech and Hearing

Word Error Rate Minimization Using an Integrated Confidence Measure

Akio KOBAYASHI1, Kazuo ONOE1, Shinichi HOMMA1, Shoei SATO1 and Toru IMAI1

1 The authors are with NHK Science and Technical Research Laboratories, Tokyo, 157–8510 Japan. E-mail: kobayashi.a-fs{at}nhk.or.jp


  Abstract

This paper describes a new criterion for speech recognition using an integrated confidence measure to minimize the word error rate (WER). The conventional criteria for WER minimization obtain the expected WER of a sentence hypothesis merely by comparing it with other hypotheses in an n-best list. The proposed criterion estimates the expected WER by using an integrated confidence measure with word posterior probabilities for a given acoustic input. The integrated confidence measure, which is implemented as a classifier based on maximum entropy (ME) modeling or support vector machines (SVMs), is used to acquire probabilities reflecting whether the word hypotheses are correct. The classifier is comprised of a variety of confidence measures and can deal with a temporal sequence of them to attain a more reliable confidence. Our proposed criterion for minimizing WER achieved a WER of 9.8% and a 3.9% reduction, relative to conventional n-best rescoring methods in transcribing Japanese broadcast news in various environments such as under noisy field and spontaneous speech conditions.

Key Words: word error rate minimization, maximum entropy, support vector machines, n-best rescoring

Manuscript received June 30, 2006. Manuscript revised October 23, 2006.


Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?




Disclaimer:
Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.