IEICE TRANSACTIONS on Information
Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005
Summary :
In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis system called Nitech-HTS 2005. This paper describes the technical details, building processes, and performance of our system. We first give an overview of the basic HMM-based speech synthesis system, and then describe new features integrated into Nitech-HTS 2005 such as STRAIGHT-based vocoding, HSMM-based acoustic modeling, and a speech parameter generation algorithm considering GV. Constructed Nitech-HTS 2005 voices can generate speech waveforms at 0.3
- Publication
- IEICE TRANSACTIONS on Information Vol.E90-D No.1 pp.325-333
- Publication Date
- 2007/01/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- Type of Manuscript
- PAPER
- Category
- Speech and Hearing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Heiga ZEN, Tomoki TODA, Masaru NAKAMURA, Keiichi TOKUDA, "Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 1, pp. 325-333, January 2007, doi: .
Abstract: In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis system called Nitech-HTS 2005. This paper describes the technical details, building processes, and performance of our system. We first give an overview of the basic HMM-based speech synthesis system, and then describe new features integrated into Nitech-HTS 2005 such as STRAIGHT-based vocoding, HSMM-based acoustic modeling, and a speech parameter generation algorithm considering GV. Constructed Nitech-HTS 2005 voices can generate speech waveforms at 0.3
URL: https://global.ieice.org/en_transactions/information/10.1587/e90-d_1_325/_p
Copy
@ARTICLE{e90-d_1_325,
author={Heiga ZEN, Tomoki TODA, Masaru NAKAMURA, Keiichi TOKUDA, },
journal={IEICE TRANSACTIONS on Information},
title={Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005},
year={2007},
volume={E90-D},
number={1},
pages={325-333},
abstract={In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis system called Nitech-HTS 2005. This paper describes the technical details, building processes, and performance of our system. We first give an overview of the basic HMM-based speech synthesis system, and then describe new features integrated into Nitech-HTS 2005 such as STRAIGHT-based vocoding, HSMM-based acoustic modeling, and a speech parameter generation algorithm considering GV. Constructed Nitech-HTS 2005 voices can generate speech waveforms at 0.3
keywords={},
doi={},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005
T2 - IEICE TRANSACTIONS on Information
SP - 325
EP - 333
AU - Heiga ZEN
AU - Tomoki TODA
AU - Masaru NAKAMURA
AU - Keiichi TOKUDA
PY - 2007
DO -
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2007
AB - In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis system called Nitech-HTS 2005. This paper describes the technical details, building processes, and performance of our system. We first give an overview of the basic HMM-based speech synthesis system, and then describe new features integrated into Nitech-HTS 2005 such as STRAIGHT-based vocoding, HSMM-based acoustic modeling, and a speech parameter generation algorithm considering GV. Constructed Nitech-HTS 2005 voices can generate speech waveforms at 0.3
ER -
English
