Presentation 2014-03-06
About the Speech Recognition of Acoustically Similar Words under the Noise Environment
Yoshiyuki MIYAZAKI, Yasuhito ARAKANE, Yoshikazu MIYANAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose the method which improves the speech recognition accuracy of acoustically similar words. For example when there is a different consonant in two acoustically similar words where the sequences of their vowels are same, it is difficult to recognize them correctly under noise circumstances. In our propose system, after a conventional HMM based speech recognition is applied, acoustically difference in these words is estimated and then noise robust speech recognition is again applied for their precise speech features. As a result, it is shown that the recognition accuracy can be improved under any environments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech recognition / similar words / Noise robust / Hidden Markov model / Viterbi alignment
Paper # SIS2013-57
Date of Issue

Conference Information
Committee SIS
Conference Date 2014/2/27(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) About the Speech Recognition of Acoustically Similar Words under the Noise Environment
Sub Title (in English)
Keyword(1) Speech recognition
Keyword(2) similar words
Keyword(3) Noise robust
Keyword(4) Hidden Markov model
Keyword(5) Viterbi alignment
1st Author's Name Yoshiyuki MIYAZAKI
1st Author's Affiliation Production Department, RayTron, INC.()
2nd Author's Name Yasuhito ARAKANE
2nd Author's Affiliation Production Department, RayTron, INC.
3rd Author's Name Yoshikazu MIYANAGA
3rd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2014-03-06
Paper # SIS2013-57
Volume (vol) vol.113
Number (no) 467
Page pp.pp.-
#Pages 6
Date of Issue