Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System Sang-Jin KIM Jong-Jin KIM Minsoo HAHN Publication 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) Category: Keyword: HMM-based speech synthesis, speech synthesis, HMM, context clustering, Korean, Full Text: PDF(413.8KB)>>
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. | ||||||||||
| ||||||||||
