Presentation 2016-05-12
The Threshold Value Control Method Considering the apriori probability on quiz answer speech recognition
Hiroyuki Nishi, Yoshimasa Kimura, Toshio Kakinoki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As in the information input in the smart phone and car navigation systems, speech recognition is often used in applications in order to identify a word or words in the dictionary. However, in the task of quiz, the system is required to determine whether the answer's voice is correct or not for question. In this situation, the prior probability of the correct answer word can not be obtained from the large number of documents. It depends on the difficulty of the question. This report proposes the new method to identify whether a correct answer is included in the speech or not using the error rate and the rejection rate required as the design condition of the system
Keyword(in Japanese) (See Japanese page)
Keyword(in English) quiz / speech recognition / prior probability / recognition score / accuracy
Paper # LOIS2016-7
Date of Issue 2016-05-05 (LOIS)

Conference Information
Committee LOIS / IPSJ-SPT / IPSJ-GN
Conference Date 2016/5/12(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Manabu Okamoto(NTT) / Kanta Matsuura(Univ. of Tokyo) / Satoshi Ichimura(*)
Vice Chair Hiroyuki Nishi(Sojo Univ.)
Secretary Hiroyuki Nishi(Tsuda College) / (NTT) / (Tsuda College)
Assistant Yu Ichifuji(NII)

Paper Information
Registration To Technical Committee on Life Intelligence and Office Information Systems / Special Interest Group on Security Psychology and Trust / Special Interest Group on Groupware and Network Services
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Threshold Value Control Method Considering the apriori probability on quiz answer speech recognition
Sub Title (in English)
Keyword(1) quiz
Keyword(2) speech recognition
Keyword(3) prior probability
Keyword(4) recognition score
Keyword(5) accuracy
1st Author's Name Hiroyuki Nishi
1st Author's Affiliation Sojo University(Sojo Univ.)
2nd Author's Name Yoshimasa Kimura
2nd Author's Affiliation Sojo University(Sojo Univ.)
3rd Author's Name Toshio Kakinoki
3rd Author's Affiliation Sojo University(Sojo Univ.)
Date 2016-05-12
Paper # LOIS2016-7
Volume (vol) vol.116
Number (no) LOIS-23
Page pp.pp.33-38(LOIS),
#Pages 6
Date of Issue 2016-05-05 (LOIS)