Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19694
標題: 利用語意角色關係解決台語文轉音系統中詞被分開之發音歧異
Using the Relationship of Semantic Roles to Solve the Problem of Separated Words in a Chinese to Taiwanese TTS system
作者: 廖盈智
Liao, Ying-Chih
關鍵字: separated words
詞被分開
Polysemy problems
Semantic Roles
and Chinese to Taiwanese TTS systems
一詞多音問題
語意角色
中文轉台語文轉音系統
出版社: 資訊科學與工程學系所
引用: [1] 林義証、余明興、林金玉, “中文轉台語文轉音系統中一詞多音預測”, 第十二屆人工智慧與應用研討會(TAAI 2007), 雲林, 2007。 [2] 林義証, 余明興, 林金玉, 林元淳 (2007), “利用階層方式預測台語文轉音系統中之一詞多音”, 全國計算機會議(2007 National Computer Symposium, NCS 2007), 台中,2007。 [3] H. Bao, A. Wang, and S. Lu, “A Study of Evaluation Method for Synthetic Mandarin Speech”, Proceedings of ISCSLP 2002, The Third International Symposium on Chinese Spoken Language Processing, pp. 383-386. [4] S. H. Chen, S. H. Hwang, and Y. R. Wang, “A Mandarin Text-to-Speech System”, Computational Linguistics and Chinese Language Processing, Vol. 1, No. 1, Aug. 1996, pp. 87-100. [5] C. C. Ho, “A Hybrid Statistical/RNN Approach to Prosody Synthesis for Taiwanese TTS,” Master thesis, Department of Communication Engineering, National Chiao Tung University, 2000. [6] J. Y. Hunag, “Implementation of Tone Sandhi Rules and Tagger for Taiwanese TTS”, Master thesis, Department of Communication Engineering, National Chiao Tung University, 2001. [7] C. H. Hwang, “Text to Pronunciation Conversion in Taiwanese”, Master thesis, Institute of Statistics, National Tsing Hua University, 1996. [8] Y. J. Lin, W. S. Ji, M. S. Yu, and S. D. Lee, “Some Important Issues on Text Analysis in a Chinese to Taiwanese TTS Ssystem,” Proceedings of the 9th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA2005), May 2005, pp. 186-189. [9] Y. J. Lin, and M. S. Yu, “Using Language Models to Solve the Polysemy Problems in a Chinese to Taiwanese TTS System — the Case of “我們”,” Proceedings of The 10th Conference of Artificial Intelligence (International Track of TAAI 2005), Kaohsiung, 2005. [10] Y. J. Lin and M. S. Yu, “An Efficient Mandarin Text-to-Speech System on Time Domain”, IEICE Transactions on Information and Systems, Vol. E81-D, No. 6, June 1998, pp. 545-555. [11] Y. J. Lin, M. S. Yu, and C. J. Huang, “The Polysemy Problems, An Important Issue in a Chinese to Taiwanese TTS System”, Proceedings of the 2008 International Congress on Image and Signal Processing , Paper number P1234, May 28-30, Sanya, China, 2008. [12] Y. J. Lin, M. S. Yu, and C. Y. Lin, “Using Chi- Square Automatic Interaction Detector to Solve the Polysemy Problems in a Chinese to Taiwanese TTS System” in Proceeding of The 8th International Conference on Intelligent Systems Design and Applications (ISDA 2008), December 2008, pp.362-367. [13] M. S. Liang, R. C. Yang, Y. C. Chiang, D. C. Lyu, and R. Y. Lyu, “A Taiwanese Text-to-Speech System with Application to Language Learning”, Proceedings of the IEEE International Conference on Advanced Learning Technologies, 2004. [14] H. M. Lu, “An Implementation and Analysis of Mandarin Speech Synthesis Technologies”, M. S. Thesis, Institute of Communication Engineering, National Chiao-Tung University, June 2002. [15] C. Shih and R. Sproat, “Issues in Text-to-Speech Conversion for Mandarin”, Computational Linguistics and Chinese Language Processing, Vol., 1, No. 1, Aug. 1996, pp. 37-86. [16] C. H. Wu, C. C. Hsia, J. F. Chen, and J. F. Wang, ”Variable-Length Unit Selection in TTS Using Structural Syntactic Cost”, IEEE Transactions on Audio, Speech, and Language Processing, Vol. 15, No.4, pp. 1227-1235, May 2007. [17] Y. C. Yang, “An Implementation of Taiwanese Text-to-Speech System”, Master thesis, Department of Communication Engineering, National Chiao Tung University, 1999. [18] M. S. Yu, T. Y. Chang, T. H. Hsu, and Y. H. Tsai, “A Mandarin Text-to-Speech System Using Prosodic Hierarchy and a Large Number of Words”, Proceedings of the 17th Conference on Computational Linguistics and Speech Processing, (ROCLING XVII), pp. 183-202, Sep. 15-16, 2005, Tainan, Taiwan.
摘要: This paper brings up an urgent problem, the separated words, which should be solved in a Chinese to Taiwanese TTS system. The so called separated word is that the characters of a Chinese word are apart because of some writing habit. For instance, the Chinese word “洗澡” (take a bath) can be found in a sentence like “洗了一個舒服的澡” (take a comfortable bath). If the text analysis module in a Chinese to Taiwanese TTS system can not recognize that the two characters “洗”(wash) and “澡”(bath) belong to the same word “洗澡”(take a bath), the ambiguity of pronunciations can not be resolved. Thus it will lead to lower comprehensibility of the TTS system. We proposed an approach operated on the parsing tree to determine whether some characters are separated from the same word. Results show that our approach can achieve accuracy of 88.63%.
URI: http://hdl.handle.net/11455/19694
其他識別: U0005-1708201016183900
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1708201016183900
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.