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
  • [1] 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
  • [2] CROSS-LINGUAL TEXT-TO-SPEECH VIA HIERARCHICAL STYLE TRANSFER
    Lee, Sang-Hoon
    Choi, Ha-Yeong
    Lee, Seong-Whan
    2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024, 2024, : 25 - 26
  • [3] Expressive Text-to-Speech using Style Tag
    Kim, Minchan
    Cheon, Sung Jun
    Choi, Byoung Jin
    Kim, Jong Jin
    Kim, Nam Soo
    INTERSPEECH 2021, 2021, : 4663 - 4667
  • [4] Slovenian text-to-speech system
    Sef, T
    ISCAS 2000: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - PROCEEDINGS, VOL V: EMERGING TECHNOLOGIES FOR THE 21ST CENTURY, 2000, : 41 - 44
  • [5] PVAE-TTS: ADAPTIVE TEXT-TO-SPEECH VIA PROGRESSIVE STYLE ADAPTATION
    Lee, Ji-Hyun
    Lee, Sang-Hoon
    Kim, Ji-Hoon
    Lee, Seong-Whan
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 6312 - 6316
  • [6] 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 - +
  • [7] A TEXT-TO-SPEECH CONVERSION SYSTEM
    KLATT, DH
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 1982, 184 (SEP): : 11 - CINF
  • [8] Text-to-speech system for Danish
    1600, Publ by Elsevier Science Publishers B.V., Amsterdam, Neth
  • [9] 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
  • [10] 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 - +