Presentation	1998/11/20 Estimation of Word Spotting Accuracy Based on Simulation of Speech Recognition Yoichi Yamashita,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper proposes a method of estimating accuracy of word spotting. It is compared with the estimation based on the length of the word. Correct detections and false alarms are estimated by a new measure calculated by simulation of speech recognition for phoneme sequences that the language model generates. The simulation-based measure better performance for the estimation of false alarms. On the other hand, the length of the word has larger correlation with the spotting score for correct detections than the simulation-based measure. It is also shown that the estimation of false alarms can be a good measure of score normalization for the word spotting.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	word spotting / false alarm / FOM / speech recognition / score normalization
Paper #	SP98-95
Date of Issue

Conference Information
Committee	SP
Conference Date	1998/11/20(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	Speech (SP)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Estimation of Word Spotting Accuracy Based on Simulation of Speech Recognition
Sub Title (in English)
Keyword(1)	word spotting
Keyword(2)	false alarm
Keyword(3)	FOM
Keyword(4)	speech recognition
Keyword(5)	score normalization
1st Author's Name	Yoichi Yamashita
1st Author's Affiliation	Dep.of Computer Science, Ritsumeikan University()
Date	1998/11/20
Paper #	SP98-95
Volume (vol)	vol.98
Number (no)	424
Page	pp.pp.-
#Pages	6
Date of Issue