A Training Method of Average Voice Model for HMM-Based Speech Synthesis

Search this Article

Author(s)

    • YAMAGISHI Junichi
    • Interdisciplinary Graduate School of Science and Engineering. Tokyo Institute of Technology
    • TAMURA Masatsune
    • Interdisciplinary Graduate School of Science and Engineering. Tokyo Institute of Technology
    • MASUKO Takashi
    • Interdisciplinary Graduate School of Science and Engineering. Tokyo Institute of Technology
    • KOBAYASHI Takao
    • Interdisciplinary Graduate School of Science and Engineering. Tokyo Institute of Technology

Abstract

This paper describes a new training method of average voice model for speech synthesis in which arbitrary speaker's voice is generated based on speaker adaptation. When the amount of training data is limited, the distributions of average voice model often have bias depending on speaker and/or gender and this will degrade the quality of synthetic speech. In the proposed method, to reduce the influence of speaker dependence, we incorporate a context clustering technique called shared decision tree context clustering and speaker adaptive training into the training procedure of average voice model. From the results of subjective tests, we show that the average voice model trained using the proposed method generates more natural sounding speech than the conventional average voice model. Moreover, it is shown that voice characteristics and prosodic features of synthetic speech generated from the adapted model using the proposed method are closer to the target speaker than the conventional method.

Journal

  • IEICE Trans. Fundamentals, A

    IEICE Trans. Fundamentals, A 86(8), 1956-1963, 2003-08-01

    The Institute of Electronics, Information and Communication Engineers

References:  18

Cited by:  15

Codes

  • NII Article ID (NAID)
    110003221277
  • NII NACSIS-CAT ID (NCID)
    AA10826239
  • Text Lang
    ENG
  • Article Type
    Journal Article
  • ISSN
    09168508
  • Data Source
    CJP  CJPref  NII-ELS 
Page Top