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
  • [21] TTTS: TURKISH TEXT-TO-SPEECH SYSTEM
    Gormez, Zeliha
    Orhan, Zeynep
    PROCEEDINGS OF THE 12TH WSEAS INTERNATIONAL CONFERENCE ON COMPUTERS , PTS 1-3: NEW ASPECTS OF COMPUTERS, 2008, : 977 - +
  • [22] Japanese Text-to-Speech Conversion System
    1600, (The International Society for Computers and Their Applications (ISCA)):
  • [23] Whistler: A trainable text-to-speech system
    Huang, XD
    Acero, A
    Adcock, J
    Hon, HW
    Goldsmith, J
    Liu, JS
    Plumpe, M
    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2387 - 2390
  • [24] TEXT-TO-SPEECH TRANSLATION SYSTEM FOR ITALIAN
    LESMO, L
    MEZZALAMA, M
    TORASSO, P
    INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1978, 10 (05): : 569 - 591
  • [25] MORPHOPHONOLOGY IN THE CSTR TEXT-TO-SPEECH SYSTEM
    SHOCKEY, L
    PROCEEDINGS : INSTITUTE OF ACOUSTICS, VOL 8, PART 7: SPEECH & HEARING, 1986, 8 : 393 - 398
  • [26] Dealing with prosody in a text-to-speech system
    Goldsmith, John
    International Journal of Speech Technology, 1999, 3 (01): : 51 - 63
  • [27] EXPERIMENTAL TEXT-TO-SPEECH SYSTEM FOR HANDICAPPED
    CARLSON, R
    GRANSTROM, B
    JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1978, 64 : S163 - S163
  • [28] Dealing with prosody in a text-to-speech system
    Goldsmith J.
    International Journal of Speech Technology, 1999, 3 (1) : 51 - 63
  • [29] Spoken-style explanation generator for Japanese Kanji using a text-to-speech system
    Ooyama, Y
    Asano, H
    Matsuoka, K
    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1369 - 1372
  • [30] Part of Speech Tagging for Romanian Text-to-Speech System
    Teodorescu, Lucian Radu
    Boldizsar, Razvan
    Ordean, Mihai
    Duma, Melania
    Detesan, Laura
    Ordean, Mihaela
    13TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2011), 2012, : 153 - 159