High-Quality Prosody Generation in Mandarin Text-to-Speech System

被引：0

作者：

Guo, Qing ^{[1
]}

Zhang, Jie ^{[1
]}

Katae, Nobuyuki ^{[2
]}

Yu, Hao ^{[1
]}

机构：

[1] Fujitsu Res & Dev Ctr Co Ltd, Beijing, Peoples R China

[2] Fujitsu Labs Ltd, Kawasaki, Kanagawa 211, Japan

来源：

FUJITSU SCIENTIFIC & TECHNICAL JOURNAL | 2010年 / 46卷 / 01期

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A text-to-speech (TTS) synthesizer is a computer-based system that can automatically read text aloud. Fujitsu is developing a Mandarin TTS system using state-of-the-art technologies. The prosodic structure of synthesized text provides important information for making synthetic speech produced by a TTS system more natural and understandable. This paper describes a global probability estimation method for predicting prosodic words, which are the lowest constituent of the prosodic structure. Experimental results for this method are very promising. They are better than those for our previous binary prosodic tree method in terms of both accuracy and memory cost.

引用

页码：40 / 46

页数：7

共 50 条

[1] High-quality prosody generation in Mandarin text-to-speech system
Guo, Qing
Zhang, Jie
Katae, Nobuyuki
Yu, Hao
Fujitsu Scientific and Technical Journal, 2010, 46 (01): : 40 - 46
[2] Prosody model in a Mandarin Text-to-Speech System based on a hierarchical approach
Pan, NH
Jen, WT
Yu, SS
Yu, MS
Huang, SY
Wu, MJ
2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III, 2000, : 448 - 451
[3] AUTOMATIC PROSODY GENERATION IN A TEXT-TO-SPEECH SYSTEM FOR HEBREW
Popovic, Branislav
Knezevic, Dragan
Secujski, Milan
Pekar, Darko
FACTA UNIVERSITATIS-SERIES ELECTRONICS AND ENERGETICS, 2014, 27 (03) : 467 - 477
[4] A Mandarin text-to-speech system
Hwang, SH
Chen, SH
Wang, YR
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1421 - 1424
[5] A statistical model with hierarchical structure for predicting prosody in a mandarin text-to-speech system
Yu, MS
Pan, NH
JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS, 2005, 28 (03) : 385 - 399
[6] Dealing with prosody in a text-to-speech system
Goldsmith, John
International Journal of Speech Technology, 1999, 3 (01): : 51 - 63
[7] Dealing with prosody in a text-to-speech system
Goldsmith J.
International Journal of Speech Technology, 1999, 3 (1) : 51 - 63
[8] High-quality text-to-speech synthesis: An overview
Dutoit, T.
Journal of Electrical and Electronics Engineering, Australia, 1997, 17 (01): : 25 - 36
[9] Text normalization in mandarin Text-to-Speech system
Jia, Yuxiang
Huang, Dezhi
Liu, Wu
Dong, Yuan
Yu, Shiwen
Wang, Haila
2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4693 - +
[10] A novel prosody adaptation method for Mandarin concatenation-based text-to-speech system
Yu, Jian
Tao, Jianhua
ACOUSTICAL SCIENCE AND TECHNOLOGY, 2009, 30 (01) : 33 - 41

← 1 2 3 4 5 →