Presentation 2014-12-16
Articulatory Controllable Speech Modification using Sequential Inversion and Production Mapping with Gaussian Mixture Models
TOBING Patrick LUMBAN, Tomoki TODA, Graham NEUBIG, Sakriani SAKTI, Satoshi NAKAMURA, Ayu PURWARIANTI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose an articulatory controllable speech modification framework using statistical inversion and production mapping with Gaussian Mixture Models. The proposed framework enables us to modify speech waveforms by manipulating unobserved articulatory parameters estimated in the inversion mapping and generating the modified speech waveforms from the manipulated articulatory parameters in the production mapping. We also propose an articulatory manipulation method that considers inter-dimensional correlation between articulators. The experimental results show that the proposed framework is capable of successfully modifying phoneme sounds by manually controlling related articulators.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech modification / articulatory control / inversion mapping / production mapping / Gaussian Mixture Models
Paper # SP2014-111
Date of Issue

Conference Information
Committee SP
Conference Date 2014/12/8(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Articulatory Controllable Speech Modification using Sequential Inversion and Production Mapping with Gaussian Mixture Models
Sub Title (in English)
Keyword(1) speech modification
Keyword(2) articulatory control
Keyword(3) inversion mapping
Keyword(4) production mapping
Keyword(5) Gaussian Mixture Models
1st Author's Name TOBING Patrick LUMBAN
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Tomoki TODA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Graham NEUBIG
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
4th Author's Name Sakriani SAKTI
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
5th Author's Name Satoshi NAKAMURA
5th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
6th Author's Name Ayu PURWARIANTI
6th Author's Affiliation School of Electrical Engineering and Informatics, Institut Teknologi Bandung
Date 2014-12-16
Paper # SP2014-111
Volume (vol) vol.114
Number (no) 365
Page pp.pp.-
#Pages 6
Date of Issue