Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007

Junichi Yamagishi; Takashi Nose; Heiga Zen; Tomoki Toda; Keiichi Tokuda

doi:10.1109/ICASSP.2008.4518520

Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007

Junichi Yamagishi, Takashi Nose, Heiga Zen, Tomoki Toda, Keiichi Tokuda

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

12 Citations (Scopus)

Abstract

This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named "HTS-2007", employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than that of speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available.

Original language	English
Title of host publication	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages	3957-3960
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2008.4518520
Publication status	Published - 2008
Externally published	Yes
Event	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States Duration: 2008 Mar 31 → 2008 Apr 4

Publication series

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

Other

Other	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Country/Territory	United States
City	Las Vegas, NV
Period	08/3/31 → 08/4/4

Keywords

Blizzard Challenge
HMM
HTS
Speaker adaptation
Speech synthesis

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2008.4518520

Cite this

Yamagishi, J., Nose, T., Zen, H., Toda, T., & Tokuda, K. (2008). Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 3957-3960). [4518520] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4518520

Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007. / Yamagishi, Junichi; Nose, Takashi; Zen, Heiga et al.

2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 3957-3960 4518520 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Yamagishi, J, Nose, T, Zen, H, Toda, T & Tokuda, K 2008, Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4518520, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 3957-3960, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 08/3/31. https://doi.org/10.1109/ICASSP.2008.4518520

Yamagishi J, Nose T, Zen H, Toda T, Tokuda K. Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 3957-3960. 4518520. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2008.4518520

Yamagishi, Junichi ; Nose, Takashi ; Zen, Heiga et al. / Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. pp. 3957-3960 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{5312f7c3c96b460fb4d7b51e37e466ea,

title = "Performance evaluation of the speaker-independent HMM-based speech synthesis system {"}HTS-2007{"} for the Blizzard Challenge 2007",

abstract = "This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named {"}HTS-2007{"}, employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than that of speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available.",

keywords = "Blizzard Challenge, HMM, HTS, Speaker adaptation, Speech synthesis",

author = "Junichi Yamagishi and Takashi Nose and Heiga Zen and Tomoki Toda and Keiichi Tokuda",

year = "2008",

doi = "10.1109/ICASSP.2008.4518520",

language = "English",

isbn = "1424414849",

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

pages = "3957--3960",

booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

note = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP ; Conference date: 31-03-2008 Through 04-04-2008",

}

TY - GEN

T1 - Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007

AU - Yamagishi, Junichi

AU - Nose, Takashi

AU - Zen, Heiga

AU - Toda, Tomoki

AU - Tokuda, Keiichi

PY - 2008

Y1 - 2008

N2 - This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named "HTS-2007", employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than that of speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available.

AB - This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named "HTS-2007", employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than that of speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available.

KW - Blizzard Challenge

KW - HMM

KW - HTS

KW - Speaker adaptation

KW - Speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=51449103919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449103919&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4518520

DO - 10.1109/ICASSP.2008.4518520

M3 - Conference contribution

AN - SCOPUS:51449103919

SN - 1424414849

SN - 9781424414840

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

SP - 3957

EP - 3960

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

Y2 - 31 March 2008 through 4 April 2008

ER -

Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this