State duration modeling for HMM-based speech synthesis

被引：4
|
作者：
Zen, Heiga [1 ]
Masuko, Takashi
Tokuda, Keiichi
Yoshimura, Takayoshi
Kobayasih, Takao
Kitamura, Tadashi
机构：
[1] Nagoya Inst Technol, Dept Comp Sci & Engn, Nagoya, Aichi 4668555, Japan
[2] Tokyo Inst Technol, Interdisciplinary Grad Sch Sci & Engn, Yokohama, Kanagawa 2268502, Japan
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2007年 / E90D卷 / 03期
关键词：
duration modeling; speech synthesis; hidden Markov model;
D O I：
10.1093/ietisy/e90-d.3.692
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the state duration PDF and demonstrate improvements in the duration of synthesized speech.
引用
收藏
页码：692 / 693
页数：2
相关论文
共 50 条
  • [31] Optimal Number of States in HMM-Based Speech Synthesis
    Hanzlicek, Zdenek
    [J]. TEXT, SPEECH, AND DIALOGUE, TSD 2017, 2017, 10415 : 353 - 361
  • [32] Synthesis and evaluation of conversational characteristics in HMM-based speech synthesis
    Andersson, Sebastian
    Yamagishi, Junichi
    Clark, Robert A. J.
    [J]. SPEECH COMMUNICATION, 2012, 54 (02) : 175 - 188
  • [33] A trainable excitation model for HMM-based speech synthesis
    Maia, R.
    Toda, T.
    Zen, H.
    Nankaku, Y.
    Tokuda, K.
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1125 - +
  • [34] Speaker interpolation for HMM-based speech synthesis system
    [J]. Yoshimura, Takayoshi, 2000, Acoustical Soc Jpn, Tokyo, Japan (21):
  • [35] Contextual Additive Structure for HMM-Based Speech Synthesis
    Takaki, Shinji
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2014, 8 (02) : 229 - 238
  • [36] Parameterization of Vocal Fry in HMM-Based Speech Synthesis
    Silen, Hanna
    Helander, Elina
    Nurminen, Jani
    Gabbouj, Moncef
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1735 - +
  • [37] A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis
    Maia, Ranniery
    Toda, Tomoki
    Tokuda, Keiichi
    Sakai, Shinsuke
    Nakamura, Satoshi
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1743 - 1746
  • [38] REACTIVE AND CONTINUOUS CONTROL OF HMM-BASED SPEECH SYNTHESIS
    Astrinaki, Maria
    d'Alessandro, Nicolas
    Picart, Benjamin
    Drugman, Thomas
    Dutoit, Thierry
    [J]. 2012 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2012), 2012, : 252 - 257
  • [39] The Design and Implementation of HMM-based Dai Speech Synthesis
    Wang, Zhan
    Yang, Jian
    Yang, Xin
    [J]. 2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
  • [40] An HMM-based speech synthesis system applied to English
    Tokuda, K
    Zen, H
    Black, AW
    [J]. PROCEEDINGS OF THE 2002 IEEE WORKSHOP ON SPEECH SYNTHESIS, 2002, : 227 - 230
12345