Presentation 2004/12/15
ASR Evaluation Measure and Minimum Bayes-Risk Decoding for Open-domain Speech Understanding
Hiroaki NANJO, Tatsuya KAWAHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A new evaluation measure of speech recognition and a decoding strategy for keyword-based open-domain speech understanding are presented. Conventionally, WER (word error rate) has been widely used as an evaluation measure of speech recognition, which treats all words in a uniform manner. In this paper, we define a weighted keyword error rate (WKER) which gives a weight on errors from a viewpoint of information retrieval. We first demonstrate that this measure is more appropriate for predicting the performance of key sentence indexing of oral presentations. Then, we formulate a decoding method to minimize WKER.based on Minimum Bayes-Risk (MBR) framework, and show that the decoding method works reasonably for improving WKER and key sentence indexing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech recognition / speech understanding / key sentence extraction / Minimum Bayes-Risk decoding
Paper # NLC2004-82,SP2004-122
Date of Issue

Conference Information
Committee NLC
Conference Date 2004/12/15(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) ASR Evaluation Measure and Minimum Bayes-Risk Decoding for Open-domain Speech Understanding
Sub Title (in English)
Keyword(1) speech recognition
Keyword(2) speech understanding
Keyword(3) key sentence extraction
Keyword(4) Minimum Bayes-Risk decoding
1st Author's Name Hiroaki NANJO
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Tatsuya KAWAHARA
2nd Author's Affiliation Academic Center for Computing and Media Studies, Kyoto University
Date 2004/12/15
Paper # NLC2004-82,SP2004-122
Volume (vol) vol.104
Number (no) 540
Page pp.pp.-
#Pages 6
Date of Issue