Towards including prosody in a text-to-speech system for modern standard Arabic

被引：6
|
作者：
Ramsay, Allan [1 ]
Mansour, Hanady
机构：
[1] Univ Manchester, Sch Comp Sci, Manchester M13 9PL, Lancs, England
[2] Univ Alexandria, Alexandria, Egypt
来源：
COMPUTER SPEECH AND LANGUAGE | 2008年 / 22卷 / 01期
关键词：
text to speech; modern standard arabic; prosody;
D O I：
10.1016/j.csl.2007.06.004
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Most attempts to provide text-to-speech for modern standard Arabic (MSA) have concentrated on solving the problem of diacritic assignment (i.e. of recovering phonetically relevant information, such as choice of short vowels, which is not explicitly provided in the surface form of MSA). This is clearly a crucial issue: you can hardly produce intelligible spoken output if you do not know what the vowels are. We describe an approach to the task of generating speech from MSA text which not only solves this initial problem, but also provides the information required for imposing an appropriate intonation contour. (c) 2007 Elsevier Ltd. All rights reserved.
引用
下载
收藏
页码：84 / 103
页数：20
相关论文
共 50 条
  • [41] Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with Acoustic and Textual Contexts
    Xin, Detai
    Adavanne, Sharath
    Ang, Federico
    Kulkarni, Ashish
    Takamichi, Shinnosuke
    Saruwatari, Hiroshi
    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2023,
  • [42] A TEXT-TO-SPEECH CONVERSION SYSTEM
    KLATT, DH
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 1982, 184 (SEP): : 11 - CINF
  • [43] A Hakka text-to-speech system
    Yu, Hsiu-Min
    Hwang, Hsin-Te
    Lin, Dong-Yi
    Chen, Sin-Horng
    CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 241 - +
  • [44] 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
  • [45] Text-to-speech system for Danish
    1600, Publ by Elsevier Science Publishers B.V., Amsterdam, Neth
  • [46] Text analysis for the Slovenian text-to-speech system
    Sef, T
    ICECS 2001: 8TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, VOLS I-III, CONFERENCE PROCEEDINGS, 2001, : 1355 - 1358
  • [47] 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 - +
  • [48] Two-Stage Prosody Prediction for Emotional Text-to-Speech Synthesis
    Tang, Hao
    Zhou, Xi
    Odisio, Matthias
    Hasegawa-Johnson, Mark
    Huang, Thomas S.
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 2138 - 2141
  • [49] Novel Eigenpitch-based Prosody Model for Text-to-Speech Synthesis
    Tian, Jilei
    Nurminen, Jani
    Kiss, Imre
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 313 - 316
  • [50] EXACT PROSODY CLONING IN ZERO-SHOT MULTISPEAKER TEXT-TO-SPEECH
    Lux, Florian
    Koch, Julia
    Vu, Ngoc Thang
    2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 962 - 969
12345