Presentation 2007/3/2
Application and Performance evaluation of RSF/DRA to Various Acostic Features in Speech Recognition
Masanori SUKEGAWA, Noboru HAYASAKA, Yoshikazu MIYANAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As a robust speech recognition system, we have proposed RSF and DRA. The RSF is a noise robust technique for reducing the convolutive noise and a part of additive noise. The DRA is a technique for the adjustment between clean and noisy speech features.They are applied for MFCC features. In this report we apply RSF/DRA for not only MFCC but also BFCC and PLP features, and we compare their performances and it is shown that the RSF/DRA is effective against every features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) RSF / DRA / MFCC / PLP / mel scale / bark scale
Paper # SIS2006-85
Date of Issue

Conference Information
Committee SIS
Conference Date 2007/3/2(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Application and Performance evaluation of RSF/DRA to Various Acostic Features in Speech Recognition
Sub Title (in English)
Keyword(1) RSF
Keyword(2) DRA
Keyword(3) MFCC
Keyword(4) PLP
Keyword(5) mel scale
Keyword(6) bark scale
1st Author's Name Masanori SUKEGAWA
1st Author's Affiliation Graduate School of Information Science Technology, Hokkaido University()
2nd Author's Name Noboru HAYASAKA
2nd Author's Affiliation Graduate School of Information Science Technology, Hokkaido University
3rd Author's Name Yoshikazu MIYANAGA
3rd Author's Affiliation Graduate School of Information Science Technology, Hokkaido University
Date 2007/3/2
Paper # SIS2006-85
Volume (vol) vol.106
Number (no) 576
Page pp.pp.-
#Pages 6
Date of Issue