Presentation 2005-12-16
[Tutorial] Speech Information Processing and Speech Corpora
Kazuya TAKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Statistical approaches for modeling and training Spoken Language Systems (SLS) using large speech corpora have improved the performance of various SLS applications. In this paper, the overview of the fundamental technologies in SLS's and the research progress of those technologies are described together with how the individual speech corpus contributes for the development.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech recognition / Speech corpora / Acoustic model / Language model
Paper # PRMU2005-129
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/12/9(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Tutorial] Speech Information Processing and Speech Corpora
Sub Title (in English)
Keyword(1) Speech recognition
Keyword(2) Speech corpora
Keyword(3) Acoustic model
Keyword(4) Language model
1st Author's Name Kazuya TAKEDA
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
Date 2005-12-16
Paper # PRMU2005-129
Volume (vol) vol.105
Number (no) 478
Page pp.pp.-
#Pages 6
Date of Issue