HMM-based Tibetan Lhasa Speech Synthesis System

被引：0
|
作者：
Wu Zhiqiang [1 ]
Yu Hongzhi [1 ]
Li Guanyu [1 ]
Wan Shuhui [1 ]
机构：
[1] Northwest Univ Nationalities, Key Lab Chinas Natl Linguist Informat Technol, Lanzhou, Peoples R China
来源：
2013 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT) | 2013年
关键词：
speech synthesis; Tibetan; hidden Markov model; synthesis by parametric modeling;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
According to the pronunciation characteristics of Tibetan Lhasa dialect, this design realizes the Tibetan Hidden Markov Model(HMM) parametric speech synthesis system. At first, we prepare data from several aspects, such as text design and recording, speech segmentation, tagging, problem sets. Then we built the Tibetan Lhasa dialect pronunciation training model and synthetic speech sound by using MLSA speech synthesizer. Finally we evaluate the quality of synthetic by using the methods of mean opinion score (MOS), the evaluation results show that the mean opinion score (MOS) was around 3.2 which basically achieve the anticipated design effect.
引用
收藏
页码：92 / 95
页数：4
相关论文
共 50 条
  • [21] An HMM-based Speech-smile Synthesis System: An Approach for Amusement Synthesis
    El Haddad, Kevin
    Dupont, Stephane
    d'Alessandro, Nicolas
    Dutoit, Thierry
    2015 11TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOPS ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG): EMOTION REPRESENTATION, ANALYSIS AND SYNTHESIS IN CONTINUOUS TIME AND SPACE (EMOSPACE 2015), VOL 5, 2015,
  • [22] Development of an HMM-Based Speech Synthesis System for Indian English Language
    Mullah, Helal Uddin
    Pyrtuh, Fidalizia
    Singh, L. Joyprakash
    2015 INTERNATIONAL SYMPOSIUM ON ADVANCED COMPUTING AND COMMUNICATION (ISACC), 2015, : 124 - 127
  • [23] Robust Pitch Extraction Method for the HMM-Based Speech Synthesis System
    Reddy, M. Kiran
    Rao, K. Sreenivasa
    IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (08) : 1133 - 1137
  • [24] Speech parameter generation algorithms for HMM-based speech synthesis
    Tokuda, K
    Yoshimura, T
    Masuko, T
    Kobayashi, T
    Kitamura, T
    2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 1315 - 1318
  • [25] Inverse filter based excitation model for HMM-based speech synthesis system
    Reddy, Mittapalle Kiran
    Rao, Krothapalli Sreenivasa
    IET SIGNAL PROCESSING, 2018, 12 (04) : 544 - 548
  • [26] State duration modeling for HMM-based speech synthesis
    Zen, Heiga
    Masuko, Takashi
    Tokuda, Keiichi
    Yoshimura, Takayoshi
    Kobayasih, Takao
    Kitamura, Tadashi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2007, E90D (03): : 692 - 693
  • [27] Analysis and HMM-based synthesis of hypo and hyperarticulated speech
    Picart, Benjamin
    Drugman, Thomas
    Dutoit, Thierry
    COMPUTER SPEECH AND LANGUAGE, 2014, 28 (02): : 687 - 707
  • [28] Optimal Number of States in HMM-Based Speech Synthesis
    Hanzlicek, Zdenek
    TEXT, SPEECH, AND DIALOGUE, TSD 2017, 2017, 10415 : 353 - 361
  • [29] Synthesis and evaluation of conversational characteristics in HMM-based speech synthesis
    Andersson, Sebastian
    Yamagishi, Junichi
    Clark, Robert A. J.
    SPEECH COMMUNICATION, 2012, 54 (02) : 175 - 188
  • [30] A trainable excitation model for HMM-based speech synthesis
    Maia, R.
    Toda, T.
    Zen, H.
    Nankaku, Y.
    Tokuda, K.
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1125 - +
12345