Towards Intonation Control in Unit Selection Speech Synthesis

被引：0
|
作者：
Boidin, Cedric [1 ]
Boeffard, Olivier [2 ]
Moudenc, Thierry [1 ]
Damnati, Geraldine [1 ]
机构：
[1] Orange Labs, Lannion, France
[2] Univ Rennes 1, ENSSAT, IRISA, Lannion, France
来源：
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | 2009年
关键词：
Speech synthesis; statistical intonation model; joint prosodic and segmental unit selection; finite state machines;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We propose to control intonation in unit selection speech synthesis with a mixed CART-HMM intonation model. The Finite State Machine (FSM) formulation is suited to incorporate the intonation model in the unit selection framework because it allows for combination of models with different unit types and handling competing intonative variants. Subjective experiments have been carried out to compare segmental and joint-prosodic-and-segmental unit selection.
引用
收藏
页码：736 / +
页数：2
相关论文
共 50 条
  • [31] Optimizing Phonetic Encoding for Viennese Unit Selection Speech Synthesis
    Pucher, Michael
    Neubarth, Friedrich
    Strom, Volker
    [J]. DEVELOPMENT OF MULTIMODAL INTERFACES: ACTIVE LISTING AND SYNCHRONY, 2010, 5967 : 207 - +
  • [32] PREDICTING SPECTRAL AND PROSODIC PARAMETERS FOR UNIT SELECTION IN SPEECH SYNTHESIS
    Dong, Minghui
    Li, Haizhou
    [J]. 2008 6TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2008, : 133 - 136
  • [33] Unit Selection based Speech Synthesis for Poor Channel Condition
    Cen, Ling
    Dong, Minghui
    Chan, Paul
    Li, Haizhou
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2035 - 2038
  • [34] Phone-Level Embeddings for Unit Selection Speech Synthesis
    Perquin, Antoine
    Lecorve, Gwenole
    Lolive, Damien
    Amsaleg, Laurent
    [J]. STATISTICAL LANGUAGE AND SPEECH PROCESSING, SLSP 2018, 2018, 11171 : 21 - 31
  • [35] Trainable unit selection speech synthesis under statistical framework
    WANG RenHua DAI LiRong LING ZhenHua HU Yu iFLYTEK Speech Lab University of Science and Technology of China Hefei China
    [J]. Chinese Science Bulletin., 2009, 54 (11) - 1969
  • [36] Unifying Unit Selection and Hidden Markov Model Speech Synthesis
    Taylor, Paul
    [J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1758 - 1761
  • [37] On the Impact of Annotation Errors on Unit-Selection Speech Synthesis
    Matousek, Jindrich
    Tihelka, Daniel
    Smidl, Lubos
    [J]. TEXT, SPEECH AND DIALOGUE, TSD 2012, 2012, 7499 : 456 - 463
  • [38] Efficient Unit-Selection in Text-to-Speech Synthesis
    Mihelic, Ales
    Gros, Jerneja Zganec
    [J]. TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2008, 5246 : 411 - 418
  • [39] Trainable unit selection speech synthesis under statistical framework
    Wang RenHua
    Dai LiRong
    Ling ZhenHua
    Hu Yu
    [J]. CHINESE SCIENCE BULLETIN, 2009, 54 (11): : 1963 - 1969
  • [40] Joint prosody prediction and unit selection for concatenative speech synthesis
    Bulyko, I
    Ostendorf, M
    [J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING, 2001, : 781 - 784
12345