Presentation 2013-06-14
Robust Speech Recognition for Similar Pronunciation Words by Using Linear Prediction Theory
Masumi WATANABE, Yoshikazu MIYANAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a robust speech recognition method for similar pronunciation words using linear prediction theory. Along with the popularization of information devices such as smart-phones, many voice input applications have spread in the society. In order to increase the speech recognition rate under a real environment, it is extremely important to identify similar pronunciation words. We adopted linear prediction theory for extracting features. CMS/DRA, the most effective method that we investigated so far was also chosen to block noise in the similar pronunciation words. In conclusion, we managed to improve the recognition rate under the noisy circumstances.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech Recognition / Similar Pronunciation Words / Linear Prediction Theory / Robust
Paper # SIS2013-12
Date of Issue

Conference Information
Committee SIS
Conference Date 2013/6/6(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) Robust Speech Recognition for Similar Pronunciation Words by Using Linear Prediction Theory
Sub Title (in English)
Keyword(1) Speech Recognition
Keyword(2) Similar Pronunciation Words
Keyword(3) Linear Prediction Theory
Keyword(4) Robust
1st Author's Name Masumi WATANABE
1st Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University()
2nd Author's Name Yoshikazu MIYANAGA
2nd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2013-06-14
Paper # SIS2013-12
Volume (vol) vol.113
Number (no) 78
Page pp.pp.-
#Pages 6
Date of Issue