Presentation 2015-03-03
A Consideration on Deteriorated Phoneme Classification by using Haar-Wavelet for Speech Sound Super-Resolution
Yuki SUGII, Akira SANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Super-resolution is a class of methods to interpolate an image data appropriately. We aim to reconstruct an identifiable speech sound data from its deteriorated one in the super-resoluton method. For that purpose, it is necessary to identify a deteriorated data as a language phoneme after that to interpolate suitable data for the phoneme. We propose a new method of generating a classification tree for the deteriorated phonemes. In the method, each language phoneme is identified based on the combination of resolution level obtained by multiple resolution analysis using Haar-Wavelet and reduced dimension by PCA. We apply the method to deteriorated Japanese phoneme and investigate its classification ability.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Super-resolution / Haar-Wavelet / Deteriorated Phoneme / Classification tree / PCA
Paper # EA2014-111,SIP2014-152,SP2014-174
Date of Issue

Conference Information
Committee EA
Conference Date 2015/2/23(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 Engineering Acoustics (EA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Consideration on Deteriorated Phoneme Classification by using Haar-Wavelet for Speech Sound Super-Resolution
Sub Title (in English)
Keyword(1) Super-resolution
Keyword(2) Haar-Wavelet
Keyword(3) Deteriorated Phoneme
Keyword(4) Classification tree
Keyword(5) PCA
1st Author's Name Yuki SUGII
1st Author's Affiliation Graduate School of Science and Technology, Ryukoku University()
2nd Author's Name Akira SANO
2nd Author's Affiliation Graduate School of Science and Technology, Ryukoku University
Date 2015-03-03
Paper # EA2014-111,SIP2014-152,SP2014-174
Volume (vol) vol.114
Number (no) 473
Page pp.pp.-
#Pages 5
Date of Issue