State Duration Modeling for HMM-Based Speech Synthesis

Heiga ZEN  Takashi MASUKO  Keiichi TOKUDA  Takayoshi YOSHIMURA  Takao KOBAYASIH  Tadashi KITAMURA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E90-D   No.3   pp.692-693
Publication Date: 2007/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e90-d.3.692
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
duration modeling,  speech synthesis,  hidden Markov model,  

Full Text: PDF(54.1KB)
>>Buy this Article


Summary: 
This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the state duration PDF and demonstrate improvements in the duration of synthesized speech.