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

Sang-Jin KIM  Jong-Jin KIM  Minsoo HAHN  

IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.3   pp.1116-1119
Publication Date: 2006/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.3.1116
Print ISSN: 0916-8532
Type of Manuscript: Special Section LETTER (Special Section on Statistical Modeling for Speech Processing)
HMM-based speech synthesis,  speech synthesis,  HMM,  context clustering,  Korean,  

Full Text: PDF(413.8KB)>>
Buy this Article

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.