One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model

Masatsune Tamura; Masahiro Morita; Takehiko Kagoshima; Masami Akamine

doi:10.1109/ICASSP.2011.5947510

One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model

Masatsune Tamura, Masahiro Morita, Takehiko Kagoshima, Masami Akamine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Citations (Scopus)

Abstract

This paper presents a rapid voice adaptation algorithm using GMM-based frequency warping and shift with parameters of a sub-band basis spectrum model (SBM)[1]. The SBM parameter represents a shape of a spectrum of speech. It is calculated by fitting a sub-band basis to the log-spectrum. Since the parameter is the frequency domain representation, frequency warping can be directly applied to the SBM parameter. A frequency warping function that minimize the distance between source and target SBM parameter pairs in each mixture component of a GMM is derived using a DP (Dynamic programming) algorithm. The proposed method is evaluated in an unit-selection based voice adaptation framework applied to a unit-fusion based text-to-speech synthesizer. The experimental results show that the proposed adaptation method is effective for rapid voice adaptation using just one sentence, compared to the conventional GMM.-based linear transformation of mel-cepstra.

Original language	English
Title of host publication	2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
Pages	5124-5127
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2011.5947510
Publication status	Published - 2011 Aug 18
Externally published	Yes
Event	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic Duration: 2011 May 22 → 2011 May 27

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Country	Czech Republic
City	Prague
Period	11/5/22 → 11/5/27

Keywords

frequency warping
sub-band basis spectrum model
unit fusion speech synthesis
voice adaptation

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2011.5947510

Fingerprint Dive into the research topics of 'One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model'. Together they form a unique fingerprint.

Cite this

Tamura, M., Morita, M., Kagoshima, T., & Akamine, M. (2011). One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings (pp. 5124-5127). [5947510] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2011.5947510

One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model. / Tamura, Masatsune; Morita, Masahiro; Kagoshima, Takehiko; Akamine, Masami.

2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 5124-5127 5947510 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tamura, M, Morita, M, Kagoshima, T & Akamine, M 2011, One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model. in 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings., 5947510, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 5124-5127, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 11/5/22. https://doi.org/10.1109/ICASSP.2011.5947510

Tamura M, Morita M, Kagoshima T, Akamine M. One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 5124-5127. 5947510. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2011.5947510

Tamura, Masatsune ; Morita, Masahiro ; Kagoshima, Takehiko ; Akamine, Masami. / One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. pp. 5124-5127 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{29c1f3b2bc8b4b44a7b59aa64344610b,

title = "One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model",

abstract = "This paper presents a rapid voice adaptation algorithm using GMM-based frequency warping and shift with parameters of a sub-band basis spectrum model (SBM)[1]. The SBM parameter represents a shape of a spectrum of speech. It is calculated by fitting a sub-band basis to the log-spectrum. Since the parameter is the frequency domain representation, frequency warping can be directly applied to the SBM parameter. A frequency warping function that minimize the distance between source and target SBM parameter pairs in each mixture component of a GMM is derived using a DP (Dynamic programming) algorithm. The proposed method is evaluated in an unit-selection based voice adaptation framework applied to a unit-fusion based text-to-speech synthesizer. The experimental results show that the proposed adaptation method is effective for rapid voice adaptation using just one sentence, compared to the conventional GMM.-based linear transformation of mel-cepstra.",

keywords = "frequency warping, sub-band basis spectrum model, unit fusion speech synthesis, voice adaptation",

author = "Masatsune Tamura and Masahiro Morita and Takehiko Kagoshima and Masami Akamine",

year = "2011",

month = aug,

day = "18",

doi = "10.1109/ICASSP.2011.5947510",

language = "English",

isbn = "9781457705397",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "5124--5127",

booktitle = "2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings",

note = "36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 ; Conference date: 22-05-2011 Through 27-05-2011",

}

TY - GEN

T1 - One sentence voice adaptation using GMM-based frequency-warping and shift with a sub-band basis spectrum model

AU - Tamura, Masatsune

AU - Morita, Masahiro

AU - Kagoshima, Takehiko

AU - Akamine, Masami

PY - 2011/8/18

Y1 - 2011/8/18

N2 - This paper presents a rapid voice adaptation algorithm using GMM-based frequency warping and shift with parameters of a sub-band basis spectrum model (SBM)[1]. The SBM parameter represents a shape of a spectrum of speech. It is calculated by fitting a sub-band basis to the log-spectrum. Since the parameter is the frequency domain representation, frequency warping can be directly applied to the SBM parameter. A frequency warping function that minimize the distance between source and target SBM parameter pairs in each mixture component of a GMM is derived using a DP (Dynamic programming) algorithm. The proposed method is evaluated in an unit-selection based voice adaptation framework applied to a unit-fusion based text-to-speech synthesizer. The experimental results show that the proposed adaptation method is effective for rapid voice adaptation using just one sentence, compared to the conventional GMM.-based linear transformation of mel-cepstra.

AB - This paper presents a rapid voice adaptation algorithm using GMM-based frequency warping and shift with parameters of a sub-band basis spectrum model (SBM)[1]. The SBM parameter represents a shape of a spectrum of speech. It is calculated by fitting a sub-band basis to the log-spectrum. Since the parameter is the frequency domain representation, frequency warping can be directly applied to the SBM parameter. A frequency warping function that minimize the distance between source and target SBM parameter pairs in each mixture component of a GMM is derived using a DP (Dynamic programming) algorithm. The proposed method is evaluated in an unit-selection based voice adaptation framework applied to a unit-fusion based text-to-speech synthesizer. The experimental results show that the proposed adaptation method is effective for rapid voice adaptation using just one sentence, compared to the conventional GMM.-based linear transformation of mel-cepstra.

KW - frequency warping

KW - sub-band basis spectrum model

KW - unit fusion speech synthesis

KW - voice adaptation

UR - http://www.scopus.com/inward/record.url?scp=80051619373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051619373&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5947510

DO - 10.1109/ICASSP.2011.5947510

M3 - Conference contribution

AN - SCOPUS:80051619373

SN - 9781457705397

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 5124

EP - 5127

BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings

T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

Y2 - 22 May 2011 through 27 May 2011

ER -