State Duration Modeling for HMM-Based Speech Synthesis

Heiga Zen; Takashi Masuko; Keiichi Tokuda; Tetsuhiko Yoshimura; Takao Kobayasih; Takashi Kitamura

doi:10.1093/ietisy/e90-d.3.692

ScienceGate Book Chapters

JOURNAL ARTICLE

State Duration Modeling for HMM-Based Speech Synthesis

Heiga Zen Takashi Masuko Keiichi Tokuda Tetsuhiko Yoshimura Takao Kobayasih Takashi Kitamura

Year: 2007 Journal: IEICE Transactions on Information and Systems Vol: E90-D (3)Pages: 692-693 Publisher: Institute of Electronics, Information and Communication Engineers

DOI: 10.1093/ietisy/e90-d.3.692

Get Full-Text PDF Get Analytical Report

Abstract

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.

Keywords:

Computer science Hidden Markov model Duration (music) Speech recognition State (computer science) Speech synthesis Artificial intelligence Natural language processing Algorithm Acoustics

Metrics

Cited By

1.55

FWCI (Field Weighted Citation Impact)

Refs

0.86

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Speech and dialogue systems

Physical Sciences → Computer Science → Artificial Intelligence

Speech and Audio Processing

Physical Sciences → Computer Science → Signal Processing

State Duration Modeling for HMM-Based Speech Synthesis

Abstract

Metrics

Citation History

Topics

Related Documents

Full covariance state duration modeling for HMM-based speech synthesis

Duration modeling for HMM-based speech synthesis

Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis

Analysis of duration prediction accuracy in HMM-based speech synthesis

HMM retraining based on state duration alignment for noisy speech recognition