A speaker adaptation technique for mrhsmm-based style control of synthetic speech

Takashi Nose; Yoichi Kato; Takao Kobayashi

doi:10.1109/ICASSP.2007.367042

A speaker adaptation technique for mrhsmm-based style control of synthetic speech

Takashi Nose, Yoichi Kato, Takao Kobayashi

ENG - Communications Engineering

Tokyo Institute of Technology

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

17 Citations (Scopus)

Abstract

This paper describes a speaker adaptation technique for style control based on multiple regression hidden semi-Markov model (MRHSMM). In the MRHSMM-based style control technique, when available training data is very small. the resultant model would produce unnatural sounding speech. To overcome this problem, we propose a model adaptation technique for MRHSMM, which is similar to the MLLR adaptation technique used in speech recognition and speech synthesis. We formulate the model adaptation problem for MRHSMM based on a linear transformation framework and derive re-estimation formulas for transformation matrices in ML sense. We also describe the results of subjective evaluation tests.

Original language	English
Title of host publication	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Pages	IV833-IV836
DOIs	https://doi.org/10.1109/ICASSP.2007.367042
Publication status	Published - 2007
Event	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, United States Duration: 2007 Apr 15 → 2007 Apr 20

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	4
ISSN (Print)	1520-6149

Conference

Conference	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Country/Territory	United States
City	Honolulu, HI
Period	07/4/15 → 07/4/20

Keywords

Expressive speech synthesis
Hidden Markov model
MLLR
Speaker adaptation
Style control

Access to Document

10.1109/ICASSP.2007.367042

Cite this

Nose, T., Kato, Y., & Kobayashi, T. (2007). A speaker adaptation technique for mrhsmm-based style control of synthetic speech. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 (pp. IV833-IV836). Article 4218230 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 4). https://doi.org/10.1109/ICASSP.2007.367042

@inproceedings{54d527b549004ed5895bcef8eabfec8d,

title = "A speaker adaptation technique for mrhsmm-based style control of synthetic speech",

abstract = "This paper describes a speaker adaptation technique for style control based on multiple regression hidden semi-Markov model (MRHSMM). In the MRHSMM-based style control technique, when available training data is very small. the resultant model would produce unnatural sounding speech. To overcome this problem, we propose a model adaptation technique for MRHSMM, which is similar to the MLLR adaptation technique used in speech recognition and speech synthesis. We formulate the model adaptation problem for MRHSMM based on a linear transformation framework and derive re-estimation formulas for transformation matrices in ML sense. We also describe the results of subjective evaluation tests.",

keywords = "Expressive speech synthesis, Hidden Markov model, MLLR, Speaker adaptation, Style control",

author = "Takashi Nose and Yoichi Kato and Takao Kobayashi",

year = "2007",

doi = "10.1109/ICASSP.2007.367042",

language = "English",

isbn = "1424407281",

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

pages = "IV833--IV836",

booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",

note = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 ; Conference date: 15-04-2007 Through 20-04-2007",

}

Nose, T, Kato, Y & Kobayashi, T 2007, A speaker adaptation technique for mrhsmm-based style control of synthetic speech. in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07., 4218230, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 4, pp. IV833-IV836, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, Honolulu, HI, United States, 07/4/15. https://doi.org/10.1109/ICASSP.2007.367042

A speaker adaptation technique for mrhsmm-based style control of synthetic speech. / Nose, Takashi; Kato, Yoichi; Kobayashi, Takao.
2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. 2007. p. IV833-IV836 4218230 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 4).

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

TY - GEN

T1 - A speaker adaptation technique for mrhsmm-based style control of synthetic speech

AU - Nose, Takashi

AU - Kato, Yoichi

AU - Kobayashi, Takao

PY - 2007

Y1 - 2007

N2 - This paper describes a speaker adaptation technique for style control based on multiple regression hidden semi-Markov model (MRHSMM). In the MRHSMM-based style control technique, when available training data is very small. the resultant model would produce unnatural sounding speech. To overcome this problem, we propose a model adaptation technique for MRHSMM, which is similar to the MLLR adaptation technique used in speech recognition and speech synthesis. We formulate the model adaptation problem for MRHSMM based on a linear transformation framework and derive re-estimation formulas for transformation matrices in ML sense. We also describe the results of subjective evaluation tests.

AB - This paper describes a speaker adaptation technique for style control based on multiple regression hidden semi-Markov model (MRHSMM). In the MRHSMM-based style control technique, when available training data is very small. the resultant model would produce unnatural sounding speech. To overcome this problem, we propose a model adaptation technique for MRHSMM, which is similar to the MLLR adaptation technique used in speech recognition and speech synthesis. We formulate the model adaptation problem for MRHSMM based on a linear transformation framework and derive re-estimation formulas for transformation matrices in ML sense. We also describe the results of subjective evaluation tests.

KW - Expressive speech synthesis

KW - Hidden Markov model

KW - MLLR

KW - Speaker adaptation

KW - Style control

UR - http://www.scopus.com/inward/record.url?scp=34547550083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547550083&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2007.367042

DO - 10.1109/ICASSP.2007.367042

M3 - Conference contribution

AN - SCOPUS:34547550083

SN - 1424407281

SN - 9781424407286

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

SP - IV833-IV836

BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

T2 - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

Y2 - 15 April 2007 through 20 April 2007

ER -

A speaker adaptation technique for mrhsmm-based style control of synthetic speech

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this