Presentation 2007/7/19
A Flexible Temporal Decomposition-based Spectral Modification Method using Asymmetric Gaussian Mixture Model
Binh Phu Nguyen, Masato Akagi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a new spectral modification method to deal with two drawbacks of standard spectral modification methods, insufficient smoothness of the modified spectra between frames and ineffective spectral modification. A speech analysis technique called Temporal Decomposition (TD), which decomposes speech into event targets and event functions, is used to effectively model the spectral evolution. Instead of modifying the speech spectra frame by frame, we only need to modify event targets and event functions. We then proposed a new method to model and modify an event target by using asymmetric Gaussian mixture model (AGMM). Experimental results show that the effectiveness of the proposed spectral modification method is verified in terms of the smoothness of modified speech and effective spectral modification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) spectral modification / temporal decomposition / asymmetric Gaussian mixture model / STRAIGHT
Paper # SP2007-25
Date of Issue

Conference Information
Committee SP
Conference Date 2007/7/19(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) A Flexible Temporal Decomposition-based Spectral Modification Method using Asymmetric Gaussian Mixture Model
Sub Title (in English)
Keyword(1) spectral modification
Keyword(2) temporal decomposition
Keyword(3) asymmetric Gaussian mixture model
Keyword(4) STRAIGHT
1st Author's Name Binh Phu Nguyen
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Masato Akagi
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
Date 2007/7/19
Paper # SP2007-25
Volume (vol) vol.107
Number (no) 165
Page pp.pp.-
#Pages 6
Date of Issue