Presentation 2005/12/14
Information Retrieval based on Minimum Bayes-Risk Decoding considering Word Significance
Hiroaki NANJO, Teruhisa MISU, Tatsuya KAWAHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The paper addresses a new evaluation measure of automatic speech recognition (ASR) and a decoding strategy oriented for speech-based information retrieval (IR). Although word error rate (WER), which treats all words in a uniform manner, has been widely used as an evaluation measure of ASR, significance of words are different in speech understanding or IR. In this paper, we define a new ASR evaluation measure, namely, weighted word error rate (WWER) that gives a weight on errors from a viewpoint of IR. Then, we formulate a decoding method to minimize WWER based on Minimum Bayes-Risk (MBR) framework, and show that the decoding method improves WWER and IR accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech recognition / Minimum Bayes-Risk decoding / information retrieval / document retrieval
Paper # NLC2005-66,SP2005-99
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Information Retrieval based on Minimum Bayes-Risk Decoding considering Word Significance
Sub Title (in English)
Keyword(1) speech recognition
Keyword(2) Minimum Bayes-Risk decoding
Keyword(3) information retrieval
Keyword(4) document retrieval
1st Author's Name Hiroaki NANJO
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Teruhisa MISU
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Tatsuya KAWAHARA
3rd Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2005/12/14
Paper # NLC2005-66,SP2005-99
Volume (vol) vol.105
Number (no) 493
Page pp.pp.-
#Pages 6
Date of Issue