Decision-Tree-Based Markov Model for Phrase Break Prediction

ETRI Journal

关键词: speech synthesis;    TTS;    phrasing;    Prosody;   

Others  :  1185546
DOI  :  10.4218/etrij.07.0207.0003

【 摘 要 】

In this paper, a decision-tree-based Markov model for phrase break prediction is proposed. The model takes advantage of the non-homogeneous-features-based classification ability of decision tree and temporal break sequence modeling based on the Markov process. For this experiment, a text corpus tagged with parts-of-speech and three break strength levels is prepared and evaluated. The complex feature set, textual conditions, and prior knowledge are utilized; and chunking rules are applied to the search results. The proposed model shows an error reduction rate of about 11.6% compared to the conventional classification model.

   

【 参考文献 】

• [1]M.Q. Wang and J. Hirschberg, "Automatic Classification of Intonational Phrasing Boundaries," Computer Speech and Language, vol. 6, no. 2, 1992, pp. 175-196.
• [2]A.W. Black and P.A. Taylor, "Assigning Phrase Breaks from Part-of-Speech Sequences," Proc. Eurospeech, vol. 2, 1997, pp. 995-998.
• [3]M. Ostendorf and N. Veilleux, "A Hierarchical Stochastic Model for Automatic Prediction of Prosodic Boundary Location," Computational Linguistics, vol. 20, no. 1, 1994, pp. 27-52.
• [4]K. Yoon, "A Prosodic Phrasing Model for a Korean Text-to-Speech Synthesis System," Computer Speech & Language, vol. 20, no. 1, 2006, pp. 69-79.
• [5]S.S. Oh and S.H. Kim, "Modality-Based Sentence-Final Intonation Prediction for Korean Conversational-Style Text-to-Speech Systems," ETRI Journal, vol. 28, no. 6, Dec. 2006, pp. 807-810.