Presentation 2000/12/14
Automatic Archiving System for Meeting Speech
Yuya Akita, Tatsuya Kawahara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, automatic archiving system for meeting speech is presented. At first, meeting speech is segmented by the result of speaker identification using speaker GMMs, and indexed with speaker-ID and beginning/end time information. Secondly, concluding utterances are detected by spotting key-phrases including discourse markers, and automatically transcribed using topic-dependent words in the agenda or material of the meeting, and finally made into drafts of minutes. In this way, a three-layer archive including speech, indexes, and texts is generated. We made experiments on speaker identification using GMMs and key-phrase detection, and confirmed the feasibility.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech recognition / meeting speech / speaker identification / key-phrase detection / archive / minutes
Paper # NLC2000-37,SP2000-85
Date of Issue

Conference Information
Committee NLC
Conference Date 2000/12/14(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) Automatic Archiving System for Meeting Speech
Sub Title (in English)
Keyword(1) speech recognition
Keyword(2) meeting speech
Keyword(3) speaker identification
Keyword(4) key-phrase detection
Keyword(5) archive
Keyword(6) minutes
1st Author's Name Yuya Akita
1st Author's Affiliation Graduate School of Informatics Kyoto University()
2nd Author's Name Tatsuya Kawahara
2nd Author's Affiliation Graduate School of Informatics Kyoto University
Date 2000/12/14
Paper # NLC2000-37,SP2000-85
Volume (vol) vol.100
Number (no) 520
Page pp.pp.-
#Pages 6
Date of Issue