Usage of the HMM-Based Speech Synthesis for intelligent Arabic voice

被引：0
|
作者：
Fares, Tamer S. [1 ]
Khalil, Awad H. [2 ]
Hegazy, Abd El-Fatah A. [3 ]
机构：
[1] Modern Acad Maadi, Dept Comp Sci, Cairo, Egypt
[2] Amer Univ Cairo, Dept Comp Sci & Engn, Cairo, Egypt
[3] Arab Acad Sci Technol & Maritime Transport, Dept Comp Sci, Cairo, Egypt
来源：
INTELLIGENT SYSTEMS AND AUTOMATION | 2008年 / 1019卷
关键词：
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The HMM as a suitable model for time sequence modeling is used for estimation of speech synthesis parameters, A speech parameter sequence is generated from HMMs themselves whose observation vectors consists of spectral parameter vector and its dynamic feature vectors. HMMs generate cepstral coefficients and pitch parameter which are then fed to speech synthesis filter named Mel Log Spectral Approximation (MLSA), this paper explains how this approach can be applied to the Arabic language to produce intelligent Arabic speech synthesis using the HMM- Based Speech Synthesis and the influence of using of the dynamic features and the increasing of the number of mixture components on the quality enhancement of the Arabic speech synthesized.
引用
收藏
页码：93 / +
页数：2
相关论文
共 50 条
  • [41] SPEECH-LAUGHS: AN HMM-BASED APPROACH FOR AMUSED SPEECH SYNTHESIS
    El Haddad, Kevin
    Dupont, Stephane
    Urbain, Jerome
    Dutoit, Thierry
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4939 - 4943
  • [42] A HMM-based Mandarin Chinese Singing Voice Synthesis System
    Xian Li
    Zengfu Wang
    [J]. IEEE/CAA Journal of Automatica Sinica, 2016, 3 (02) : 192 - 202
  • [43] PITCH ADAPTIVE TRAINING FOR HMM-BASED SINGING VOICE SYNTHESIS
    Oura, Keiichiro
    Mase, Ayami
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 5377 - 5380
  • [44] A HMM-based Mandarin Chinese Singing Voice Synthesis System
    Li, Xian
    Wang, Zengfu
    [J]. IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2016, 3 (02) : 192 - 202
  • [45] Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
    Gia-Nhu Nguyen
    Trung-Nghia Phung
    [J]. EURASIP Journal on Audio, Speech, and Music Processing, 2017
  • [46] Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
    Gia-Nhu Nguyen
    Trung-Nghia Phung
    [J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2017,
  • [47] Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis
    Chomphan, Suphattharachai
    Kobayashi, Takao
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4637 - 4640
  • [48] Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis
    Tachibana, Makoto
    Izawa, Shinsuke
    Nose, Takashi
    Kobayashi, Takao
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4633 - 4636
  • [49] Statistical Approaches to Excitation Modeling in HMM-Based Speech Synthesis
    Sung, June Sig
    Hong, Doo Hwa
    Koo, Hyun Woo
    Kim, Nam Soo
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2013, E96D (02): : 379 - 382
  • [50] Continuous Control of the Degree of Articulation in HMM-based Speech Synthesis
    Picart, Benjamin
    Drugman, Thomas
    Dutoit, Thierly
    [J]. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 1808 - 1811
12345