Presentation 2014-07-25
Voice conversion based on sparse representation and its application to articulation disorders
Tetsuya TAKIGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, approaches based on sparse representations have gained interest in a broad range of signal processing. For example, Non-negative Matrix Factorization (NMF) is a well-known sparse-based approach for source separation and speech enhancement. In this paper, a voice conversion technique based on a sparse representation of speech using NMF is introduced, and it is applied to a person with an articulation disorder resulting from athetoid cerebral palsy. Also, in this paper, a voice conversion method using restricted Boltzmann machine, which is an important technique for deep learning, is introduced.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) voice conversion / sparse representation / articulation disorder / restricted Boltzmann machine
Paper # SP2014-66
Date of Issue

Conference Information
Committee SP
Conference Date 2014/7/17(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Voice conversion based on sparse representation and its application to articulation disorders
Sub Title (in English)
Keyword(1) voice conversion
Keyword(2) sparse representation
Keyword(3) articulation disorder
Keyword(4) restricted Boltzmann machine
1st Author's Name Tetsuya TAKIGUCHI
1st Author's Affiliation Organization of Advanced Science and Technology, Kobe University()
Date 2014-07-25
Paper # SP2014-66
Volume (vol) vol.114
Number (no) 151
Page pp.pp.-
#Pages 6
Date of Issue