Presentation 2002/6/21
Toward Spontaneous Speech Recognition and Understanding
Sadaoki Furui,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Although speech recognition technology has recently made remarkable progress, its performance for natural spontaneous speech is still quite unsatisfactory. This is one of the most important problems of the present speech recognition technology. Speech recognition tasks can be classified into four categories as to whether the speech is addressed to computers or humans and whether it is a dialogue or monologue. Among them, the research in two categories, monologue for humans and dialogue with computers, will become important hereafter. In spontaneous speech recognition, the speech understanding approach extracting contents or meanings is more important than simply converting speech into a sequence of words. This paper reports on the aims and results of the "spontaneous speech engineering" project targeting the speech recognition as well as summarization of monologues. The paper concludes with future research issues.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spontaneous speech / speech recognition / speech understanding / categories of speech recognition / spontaneous speech engineering project / speech summarization
Paper # SP2002-47
Date of Issue

Conference Information
Committee SP
Conference Date 2002/6/21(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) Toward Spontaneous Speech Recognition and Understanding
Sub Title (in English)
Keyword(1) Spontaneous speech
Keyword(2) speech recognition
Keyword(3) speech understanding
Keyword(4) categories of speech recognition
Keyword(5) spontaneous speech engineering project
Keyword(6) speech summarization
1st Author's Name Sadaoki Furui
1st Author's Affiliation Tokyo Institute of Technology, Department of Computer Science()
Date 2002/6/21
Paper # SP2002-47
Volume (vol) vol.102
Number (no) 160
Page pp.pp.-
#Pages 6
Date of Issue