Interactive Text-to-Speech System via Joint Style Analysis

被引:4
|
作者
Gao, Yang [1 ,2 ]
Zheng, Weiyi [2 ]
Yang, Zhaojun [2 ]
Koehler, Thilo [2 ]
Fuegen, Christian [2 ]
He, Qing [2 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[2] Facebook AI, Menlo Pk, CA 94025 USA
来源
关键词
Text-to-speech synthesis; emotion; style; semisupervised;
D O I
10.21437/Interspeech.2020-3069
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
While modern TTS technologies have made significant advancements in audio quality, there is still a lack of behavior naturalness compared to conversing with people. We propose a style-embedded TTS system that generates styled responses based on the speech query style. To achieve this, the system includes a style extraction model that extracts a style embedding from the speech query, which is then used by the TTS to produce a matching response. We faced two main challenges: 1) only a small portion of the TTS training dataset has style labels, which is needed to train a multi-style TTS that respects different style embeddings during inference. 2) The TTS system and the style extraction model have disjoint training datasets. We need consistent style labels across these two datasets so that the TTS can learn to respect the labels produced by the style extraction model during inference. To solve these, we adopted a semi-supervised approach that uses the style extraction model to create style labels for the TTS dataset and applied transfer learning to learn the style embedding jointly. Our experiment results show user preference for the styled TTS responses and demonstrate the style-embedded TTS system's capability of mimicking the speech query style.
引用
收藏
页码:4447 / 4451
页数:5
相关论文
共 50 条
  • [31] Natural language processing in a Japanese text-to-speech system for written-style texts
    Matsuoka, K
    Takeishi, E
    Asano, H
    THIRD IEEE WORKSHOP ON INTERACTIVE VOICE TECHNOLOGY FOR TELECOMMUNICATIONS APPLICATIONS - IVTTA-96, PROCEEDINGS, 1996, : 33 - 36
  • [32] Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge
    Guan, Wenhao
    Li, Tao
    Li, Yishuang
    Huang, Hukai
    Hong, Qingyang
    Li, Lin
    INTERSPEECH 2023, 2023, : 4304 - 4308
  • [33] ON-THE-FLY DATA AUGMENTATION FOR TEXT-TO-SPEECH STYLE TRANSFER
    Chung, Raymond
    Mak, Brian
    2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 634 - 641
  • [34] Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion
    Paul, Dipjyoti
    Shifas, Muhammed P., V
    Pantazis, Yannis
    Stylianou, Yannis
    INTERSPEECH 2020, 2020, : 1361 - 1365
  • [35] Evaluation of The Concatenative Turkish Text-to-Speech System
    Orhan, Zeynep
    Gormez, Zeliha
    PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9, 2009, : 4314 - +
  • [36] FOCUS AND ACCENT IN A DUTCH TEXT-TO-SPEECH SYSTEM
    BAART, JLG
    FOURTH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 1989, : 111 - 115
  • [37] Developing a Child Friendly Text-to-Speech System
    Jacob, Agnes
    Mythili, P.
    ADVANCES IN HUMAN-COMPUTER INTERACTION, 2008, 2008
  • [38] Implementation of a Text-to-Speech System for Kurdish Language
    Daneshfar, Fatemeh
    Barkhoda, Wafa
    Azami, Bahram Zahir
    ICDT: 2009 FOURTH INTERNATIONAL CONFERENCE ON DIGITAL TELECOMMUNICATIONS, 2009, : 117 - 120
  • [39] Towards a Modern Text-to-Speech System for Latvian
    Dargis, Roberts
    Auzina, Ilze
    HUMAN LANGUAGE TECHNOLOGIES - THE BALTIC PERSPECTIVE, BALTIC HLT 2018, 2018, 307 : 26 - 29
  • [40] Text-to-speech synthesis system for Punjabi language
    Dept. of Computer Sc. & Engg, Guru Nanak Dev Engg. College, Ludhiana
    Pb, India
    不详
    Pb, India
    Commun. Comput. Info. Sci., (302-303):