:::

詳目顯示

回上一頁
題名:A System Framework for Integrated Synthesis of Mandarin, Min-Nan, and Hakka Speech
書刊名:International Journal of Computational Linguistics & Chinese Language Processing
作者:Gu, Hung-yanZhou, Yan-zuoLiau, Huang-liang
出版日期:2007
卷期:12:4
頁次:頁371-389
主題關鍵詞:Speech synthesisPitch contour modelTIPWTime axis warping
原始連結:連回原系統網址new window
相關次數:
  • 被引用次數被引用次數:期刊(1) 博士論文(0) 專書(0) 專書論文(0)
  • 排除自我引用排除自我引用:1
  • 共同引用共同引用:3
  • 點閱點閱:17
In this paper, a framework for integrated synthesis of Mandarin, Min-nan, and Hakka speech is proposed. To show its feasibility, an initial integrated system has been built as well. Through integration, a model only trained with Min-nan sentences is used to generate pitch-contours for all three languages, same rules are used to generate syllable duration and amplitude values, and the same program module implementing the method, TIPW, is used to synthesize the three languages' speech waveforms. Also, in this system, each syllable of a language has just one recorded signal waveform, i.e. no chance of unit selection. Under such a restricted situation, the synthetic speech signals still have noticeable naturalness level and signal clarity.
期刊論文
1.Shih,Chilin、Sproat,Richard(19960800)。Issues in Text-to-Speech Conversion for Mandarin。International Journal of Computational Linguistics & Chinese Language Processing,1:1,頁37-86。new window  new window
2.陳順孝、Hwang, S. H.、Wang, Y. R.(1998)。An RNN-based prosodic information Synthesizer for Mandarin text-to-speech。IEEE Trans. Speech and Audio Proc.,6(3),226-239。  new window
3.Chiou, Hong-Bin、Wang, Hsiao-Chuan、Chang, Yueh-Chin(1991)。Synthesis of Mandarin Speech Based on Hybrid Concatentation。Computer Processing of Chinese and Oriental Languages: an international journal of the Chinese Language Computer Society,5(1),217-231。  new window
4.Gu, H. Y.、Shiu, W. L.(1998)。A Mandrain-Syllable Signal Synthesis Method with Increased Flexibility in Duration, Tone and Timbre Control。Proceedings of the National Science Coucil Science Council ROC(A),22(3),385-395。  new window
5.Lee, L. S.、Tseng, C. Y.、謝慶融(1993)。Improve Tone Concatenation Rules in a Formant-Based Chinese Text-to-Speech System。IEEE Trans. Speech and Audio Proc.,1(3),287-294。  new window
6.Wu, Chung-Hsien、Chen, J. H.(2001)。Automatic Generation of Synthesis Units and Prosodic Information for Chinese Concatenative Synthesis。Speech Communication,35(3),219-237。  new window
7.Moulines, E.、Charpentier, F.(1990)。Pitch Synchronous Waveform Processing Techniques for Text-to-Speech Synthesis Using Diphones。Speech Communication,9,453-467。  new window
會議論文
1.Chu, M.、Peng, H.、Niu, Z.、Zhao, Y.、Chang, E.(2003)。Microsoft Mulan - a Bilingual TTS System。Hong Kong。264-267。  new window
2.Gu, H. Y.、Yang, C. C.(2000)。A Sentence-Pitch-Contour Generation Method Using VQ/HMM for Mandarin Text-to-speech。Beijing。125-128。  new window
3.Gu, H. Y.(2001)。Signal Resampling in Speech Synthesis。Orlando。  new window
4.Gu, H. Y.、Tsai, H. C.(2005)。A Pitch-Contour Model Adaption Method for Intergrated Synthesis of Mandarin, Min-Nan, and Hakka Speech。Taiwan。190-193。  new window
5.Gu, H. Y.、Chuang, W. H.(2005)。Min-Nan Sentence Pitch-contour Gerneration: Mixing and Comparison of Two Kinds of Modles。  new window
6.Lee, S. J.、Kim, K. C.、Jung, H. Y.、Cho, W.(1991)。Application of Fully Recurrent Neural Networks for Speech Recognition。Toronto, Canada。70-80。  new window
7.Wang, R. H.(1998)。Overview of Chinese Text-to-Speech System。Singapore。  new window
8.Yu, M. S.、Pan, N. H.、Wu, M. J.(2002)。A Statistical Model with Hierarchical Structure for Predicting Prosody in a Mandarin Text-to-Spech System。Taipei。21-24。  new window
學位論文
1.Chou, F. C.(1999)。Corpus-based Technologies for Chinese Text-to-Speech Synthesis,Taipei。  new window
圖書
1.Rabiner, Lawrence R.、Juang, Biing-Hwang(1993)。Fundamentals of Speech Recognition。New Jersey:Prentice Hall PTR,。  new window
2.Yu, B. C.、Syu, Z. C.、Wu, C. N.(1999)。General Phonetic Symbol System for Languages in Taiwan。General Phonetic Symbol System for Languages in Taiwan。Taipei。  new window
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
QR Code
QRCODE