Multisyn voices from ARCTIC data for the Blizzard challenge

Robert A.J. Clark; Korin Richmond; Simon King

Multisyn voices from ARCTIC data for the Blizzard challenge

Robert A.J. Clark, Korin Richmond, Simon King

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

Abstract

This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.

Original language	English
Title of host publication	Interspeech 2005 - Eurospeech
Subtitle of host publication	9th European Conference on Speech Communication and Technology
Publisher	International Speech Communication Association
Pages	101-104
ISBN (Print)	1990-9772
Publication status	Published - 1 Sep 2005

Access to Document

clarkrichmondking_interspeech05
© Clark, R. A. J., Richmond, K., & King, S. (2005). Multisyn voices from ARCTIC data for the Blizzard challenge. In Interspeech 2005 - Eurospeech: 9th European Conference on Speech Communication and Technology . (pp. 101-104). International Speech Communication Association.
Accepted author manuscript, 291 KB

TESSa: Testing Evaluation of Speech Synthesis (TESSa)
King, S.
EPSRC
1/01/05 → 31/12/07
Project: Research
Expressive Prosody for Unit-selection Speech Synthesis
King, S., Clark, R. & Steedman, M.
UK central government bodies/local authorities, health and hospital authorities
1/01/04 → 29/02/12
Project: Research

Cite this

@inproceedings{1ad3658ed41a4a9ab3bb1f8bd75e1883,

title = "Multisyn voices from ARCTIC data for the Blizzard challenge",

abstract = "This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.",

author = "Clark, {Robert A.J.} and Korin Richmond and Simon King",

year = "2005",

month = sep,

day = "1",

language = "English",

isbn = "1990-9772",

pages = "101--104",

booktitle = "Interspeech 2005 - Eurospeech",

publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Multisyn voices from ARCTIC data for the Blizzard challenge

AU - Clark, Robert A.J.

AU - Richmond, Korin

AU - King, Simon

PY - 2005/9/1

Y1 - 2005/9/1

N2 - This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.

AB - This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.

M3 - Conference contribution

SN - 1990-9772

SP - 101

EP - 104

BT - Interspeech 2005 - Eurospeech

PB - International Speech Communication Association

ER -

Multisyn voices from ARCTIC data for the Blizzard challenge

Abstract

Access to Document

Fingerprint

Projects

TESSa: Testing Evaluation of Speech Synthesis (TESSa)

Expressive Prosody for Unit-selection Speech Synthesis

Cite this