Thai Speech Synthesis with emotional tone Based on Formant Synthesis for Home Robot

被引:0
|
作者
Khorinphan, Chaiyong [1 ]
Phansamdaeng, Sukanya [1 ]
Saiyod, Saiyan [1 ]
机构
[1] Khon Kean Univ, Dept Comp Sci, Khon Kaen, Thailand
关键词
Speech synthesis; Formant Frequencies; Rules; Emotional tone; Home Robot;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Home robot will have important role in near further. Human will need to communicate with robot, and vice versa. For English language, some robot can communicate with human. On the other hand, there are many limitations for Thai language. However, Thai is a tonal language which one work can be pronounced five tones including emotional tone. Therefore, there is a speech synthesis of Thai language. But, it does not adaptively perform for changing parameters which are used to generate the emotional tone. Therefore, this paper presents Thai speech synthesis with emotional tone based on Formant synthesis to synthesize Thai syllables including accent tone and emotional tone. Formant synthesis is a rule-base approach which can synthesize the speech by parameters. Fundamental frequency (f0) is an important parameter. In proposed method, the core component is the construction of intonation patterns is called rules. These rules are firstly set up in the format of Formants frequencies. The manipulation of this approach begins with substituting each phoneme of input array of phoneme of syllable with corresponded formants frequencies. Then, outcomes of this process are adapted process with parameters. We utilized 5 samples of Thai syllable for 5 people by listening in control room.
引用
收藏
页码:111 / 114
页数:4
相关论文
共 50 条
  • [1] Thai Speech Synthesis Based on Formant Synthesis for Home Robot
    Khorinphan, Chaiyong
    Saiyod, Saiyan
    Wayalun, Pichet
    2016 20TH INTERNATIONAL COMPUTER SCIENCE AND ENGINEERING CONFERENCE (ICSEC), 2016,
  • [2] FORMANT BASED SPEECH SYNTHESIS
    HUGHES, PM
    BRITISH TELECOM TECHNOLOGY JOURNAL, 1988, 6 (02): : 84 - 90
  • [3] Generalization of Thai Tone Contour in HMM-Based Speech Synthesis
    Rugchatjaroen, Anocha
    Saychum, Sittipong
    Oura, Keiichiro
    Tokuda, Keiichi
    2017 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC 2017), 2017, : 1102 - 1105
  • [4] Formant speech synthesis
    Pinto, N.B.
    Childers, D.G.
    Journal of the Institution of Electronics and Telecommunication Engineers, 1988, 34 (01): : 5 - 20
  • [5] Formant Speech Synthesis Based on Trainable Model
    Zhang, Zhiping
    Wu, Xihong
    SENSORS, MEASUREMENT AND INTELLIGENT MATERIALS, PTS 1-4, 2013, 303-306 : 1334 - 1337
  • [6] Tone correctness improvement in speaker dependent HMM-based Thai speech synthesis
    Chomphan, Suphattharachai
    Kobayashi, Takao
    SPEECH COMMUNICATION, 2008, 50 (05) : 392 - 404
  • [7] ASPECTS OF FORMANT SPEECH SYNTHESIS
    SAPOZHKO.MA
    TELECOMMUNICATIONS AND RADIO ENGINEER-USSR, 1971, (03): : 4 - +
  • [8] Speech Generation by Formant Synthesis.
    Schnautz, Horst W.
    Elektronik Munchen, 1984, 33 (23): : 160 - 165
  • [9] Statistical Formant Speech Synthesis for Arabic
    Jafri, Afshan
    Sobh, Ibrahim
    Alkhairy, Ashraf
    ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2015, 40 (11) : 3151 - 3159
  • [10] Statistical Formant Speech Synthesis for Arabic
    Afshan Jafri
    Ibrahim Sobh
    Ashraf Alkhairy
    Arabian Journal for Science and Engineering, 2015, 40 : 3151 - 3159