Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System

Sang-Jin KIM; Jong-Jin KIM; Minsoo HAHN

doi:10.1093/ietisy/e89-d.3.1116

Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System

Sang-Jin KIM, Jong-Jin KIM, Minsoo HAHN

Full Text Views

0

Share
Cite this

Summary :

Development of a hidden Markov model (HMM)-based Korean speech synthesis system and its evaluation is described. Statistical HMM models for Korean speech units are trained with the hand-labeled speech database including the contextual information about phoneme, morpheme, word phrase, utterance, and break strength. The developed system produced speech with a fairly good prosody. The synthesized speech is evaluated and compared with that of our corpus-based unit concatenating Korean text-to-speech system. The two systems were trained with the same manually labeled speech database.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.1116-1119

Publication Date: 2006/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.3.1116

Type of Manuscript: Special Section LETTER (Special Section on Statistical Modeling for Speech Processing)

Category

Cite this

Copy

Sang-Jin KIM, Jong-Jin KIM, Minsoo HAHN, "Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 3, pp. 1116-1119, March 2006, doi: 10.1093/ietisy/e89-d.3.1116.
Abstract: Development of a hidden Markov model (HMM)-based Korean speech synthesis system and its evaluation is described. Statistical HMM models for Korean speech units are trained with the hand-labeled speech database including the contextual information about phoneme, morpheme, word phrase, utterance, and break strength. The developed system produced speech with a fairly good prosody. The synthesized speech is evaluated and compared with that of our corpus-based unit concatenating Korean text-to-speech system. The two systems were trained with the same manually labeled speech database.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.1116/_p

Copy

@ARTICLE{e89-d_3_1116,
author={Sang-Jin KIM, Jong-Jin KIM, Minsoo HAHN, },
journal={IEICE TRANSACTIONS on Information},
title={Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System},
year={2006},
volume={E89-D},
number={3},
pages={1116-1119},
abstract={Development of a hidden Markov model (HMM)-based Korean speech synthesis system and its evaluation is described. Statistical HMM models for Korean speech units are trained with the hand-labeled speech database including the contextual information about phoneme, morpheme, word phrase, utterance, and break strength. The developed system produced speech with a fairly good prosody. The synthesized speech is evaluated and compared with that of our corpus-based unit concatenating Korean text-to-speech system. The two systems were trained with the same manually labeled speech database.},
keywords={},
doi={10.1093/ietisy/e89-d.3.1116},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System
T2 - IEICE TRANSACTIONS on Information
SP - 1116
EP - 1119
AU - Sang-Jin KIM
AU - Jong-Jin KIM
AU - Minsoo HAHN
PY - 2006
DO - 10.1093/ietisy/e89-d.3.1116
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - Development of a hidden Markov model (HMM)-based Korean speech synthesis system and its evaluation is described. Statistical HMM models for Korean speech units are trained with the hand-labeled speech database including the contextual information about phoneme, morpheme, word phrase, utterance, and break strength. The developed system produced speech with a fairly good prosody. The synthesized speech is evaluated and compared with that of our corpus-based unit concatenating Korean text-to-speech system. The two systems were trained with the same manually labeled speech database.
ER -