Presentation 1999/12/20
A Retrieval Method of Broadcast News Using Voice input Keywords
Hiromitsu Nishizaki, Seiichi Nakagawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To retrieve interesting broadcast news documents out of an enormous number of TV news programs, if no indexing is done on the news and word-based retrieval is required, it is inevitably necessary to transcribe all the broadcast news documents automatically and store them as a database. And this task can be done only by using a Large Vocabulary Continuous Speech Recognition(LVCSR) system. In this paper, 1) there trieval performance was experimentally compared between the system using automatically transcribed database(speech) and the one using manually transcribed database(text). This experiment was done using text as the input to the system. As a result, high recall was obtained although the word recognition rate was low. Next, 2) to solve the inevitable problem swhich arise when the input to the system is realized as speech, i.e.misrecognition, a novel method was developed. In experiments, we retrieved news documents through inputted voice keywords to the system by using the method described above and represent its effectiveness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # NLC99-40
Date of Issue

Conference Information
Committee NLC
Conference Date 1999/12/20(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 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) A Retrieval Method of Broadcast News Using Voice input Keywords
Sub Title (in English)
Keyword(1)
1st Author's Name Hiromitsu Nishizaki
1st Author's Affiliation ()
2nd Author's Name Seiichi Nakagawa
2nd Author's Affiliation
Date 1999/12/20
Paper # NLC99-40
Volume (vol) vol.99
Number (no) 523
Page pp.pp.-
#Pages 6
Date of Issue