人的說話風格包含語音、文字與肢體動作等，不僅用來強化訊息內容，更可從說話風格判斷出語者的身份。不同層次的說話風格搭配能讓訊息的表達更加活潑生動，聽者也不會感覺索然無味。近年來，說話風格的研究多偏向語音信號之範疇，缺乏文字層次的探討。因此，本論文的主要目的即透過個人習語的萃取與生成，將原始文章轉換為帶有某語者說話風格的文字訊息，達到說話風格模型化的目的。
本論文先利用統計方法自動從訓練語料中萃取出個人習語，並將之分為兩類；對於非贅語類的個人習語，設計一同義詞對照表；被歸類為贅語之個人習語，利用贅語插入模型將贅語放入文章中最合適的位置；最後藉由同義詞取代與插入贅語，將原始輸入的文章修飾成帶有目標語者說話風格的文字內容。
本研究蒐集三位台灣著名政治家的演講，並以人工謄寫為譯本。個人習語之同義詞對照表與插入模型均由譯本中自動取得。經由一系列的實驗與檢定驗證，本研究所提之方法確能將原始文章，轉換為含有目標語者說話風格之文章。

A person’s speaking style, including their voice, the vocabulary they use and the physical actions they employ while speaking, not only expresses their identity but also serves to emphasize the content of an utterance. Speech combining these aspects of speaking style is more vivid to the listener. In recent years, research on speaking style has focused mainly on speech signal processing, which neglects analysis of the text. Therefore, the purpose of this study is to convert a source text into a target text containing a certain person’s speaking style via the speaking style modeling process of idiolect extraction and generation.
The first stage of this thesis involves using a statistical method to automatically extract idiolects from the training corpus. Next, the idiolects are classified into two categories. For synonymous idiolects, a mapping table is built, while for superfluous idiolects, an insertion model is used to find suitable positions for insertion. Finally, the input text is modified to contain someone’s speaking style by way of synonym substitution and the insertion of superfluous idiolects.
To evaluate the proposed method, experiments were carried out on a corpus collected from the speeches of three Taiwanese politicians. The speeches were manually transcribed; the synonym mapping table and the insertion model were derived from the transcripts. The results show that the proposed method can effectively convert a source text into a target text with speaking style.

[1] A. Kain and M.W. Macon. “Spectral Voice Conversion for Text-To-Speech Synthesis.” Proc. ICASSP, Seattle, U.S.A., pp. 285--288, May 1998.
[2]Eichner,M ,Wolff,M. and Hoffmann,R. “Voice Characteristics Conversion for TTS Using Reverse VTLN” ICASSP’04 Vol.1,17-20
[3] T. Toda, A.W. Black, K. Tokuda, “Spectral Conversion Based on Maximum Likelihood Estimation Considering Global Variance of Converted Parameter” ICASSP’05 Vol.1, 9-12.
[4] D.T. Chappell, J.H.L. Hansen, "Speaker-Specific Pitch Contour Modeling and Modification,” IEEE ICASSP-98: Inter. Conf. on Acoustics, Speech, and Signal Processing, vol. 2, pp. 885-888, Seattle, Wash., May 1998
[5] T. En-Najjary, O. Rosec and T. Chonavel. “A New Method for Pitch Prediction From Spectral Envelope and Its Application In Voice Conversion.” Proceeding of EUROSPEECH, 2003.
[6] Verma, A., Kumar, A. “Introducing Roughness in Individuality Transformation through Jitter Modeling and Modification.” ICASSP’05 Vol.1,5-8
[7] Peter F. Brown, John Cocke, Stephen A. Della Pietra, Vincent J. Della Pietra, Fredrick Jelinek, John D. Lafferty, Robert L. Mercer, Paul S. Roossin. “A Statistical Approach to Machine Translation.” Computational Linguistics Vol.16 1990.
[8] Yujie Zhang and Kazuhide Yamamoto. “Paraphrasing of Chinese Utterances.” Proc. of Coling 2002, pp.1163-1169, 2002
[9] Regina Barzilay and Lillian Lee, “Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment ” Proceedings of HLT-NAACL 2003
[10]David Kauchak and Regina Barzilay, “Paraphrasing for Automatic Evaluation.” Proceedings of HLT-NAACL 2006, 455-462.
[11]Frank Smadja, “Retrieving Collocations from Text: Xtract” Computational Linguistics, 19(1):143–177, 1993.
[12] Christopher D. Manning and Hinrich Schutze, “Foundations of Statistical Natural Language Processing” MIT Press, 1999
[13] John S. Justeson and Slava M. Katz. “Technical terminology: Some linguistis properties and an algorithm for identification in text.” Natural Language Engineering, 1:9–27, 1995.
[14]Church K. and Hanks P. “Word Association Norms, Mutual Information, and Lexicography”, Computational Linguistics, vol.16, no.1, pp.22-29,1990
[15] Yu-Sheng Lai and Chung-Hsien Wu, “Unknown word and phrase extraction using a phrase-likeunit-based likelihood ratio,” Journal of Computer Processing of Oriental Languages, 2000
[16] Wei-Yun Ma and Keh-Jiann Chen, “A Bottom-up Merging Algorithm for Chinese Unknown Word Extraction”, Proceedings of the Second SIGHAN Workshop on Chinese Language Processing, July 2003, pp. 31-38.
[17] Chen, K.J. and Wei-Yun Ma, “Unknown Word Extraction for Chinese Documents.” In Proceedings of COLING 2002, pages 169-175
[18] RUI-FENG XU and QIN LU, “Multi-Stage Chinese Collocation Extraction” Proceedings of the 5th International Conference on Machine Learning and Cybernetics,2005
[19] Qin Lu, Yin Li and Ruifeng Xu, “An automatic Chinese collocation extraction algorithm based on lexical statistics.” In proceedings of IEEE Conf. NLPKE 2003, pages 333-338
[20] Ruifeng Xu , Yin Li and Qin Lu, “Improving Xtract for Chinese collocation extraction.” In proceedings of IEEE Conf. NLPKE 2003, pages 321-326
[21] Thomas H., Charles E., Ronald L. and Clifford Stein, “Introduction to Algorithms, Second Edition” MIT Press 2001
[22] Chen, K.J. and Ming-Hong Bai, “Unknown Word Detection for Chinese by a Corpus-based Learning Method,” international Journal of Computational linguistics and Chinese Language Processing, Vol.3, No.1, pages 27-44
[23] Chien-Cheng Wu and Jason S. Chang, “Bilingual Collocation Extraction Based on Syntactic and Statistical Analyses.” Conf. Computational Linguistics and Chinese Language Processing, Vol.9, No.1, pages 1-20, 2004
[24] David Crystal, “Language and the Internet” 2nd Edition, Cambridge University Press, 2001
[25] Redeker, G. “Ideational and pragmatic markers of discourse structure.” Journal of Pragmatics 14, 387-381, 1990
[26] A. B. Stenstrom, “An Introduction to Spoken Interaction.” Addison-Wesley, 1994.
[27] David Graff and Ke Chen “Chinese Gigaword”, LDC Catalog No.: LDC2003T09, ISBN: 1-58563-230-9
[28] Kishore Papineni , Salim Roukos , Todd Ward , Wei-Jing Zhu, “BLEU: a method for automatic evaluation of machine translation”, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, July 07-12, 2002, Philadelphia, Pennsylvania
[29] Honal, M. and Schultz, T. “Automatic Disfluency Removal on Recognized Spontaneous Speech - Rapid Adaptation to Speaker Dependent Disfluencies” ICASSP’05, Vol.1, page(s): 969- 972
[30] Snover, M., Dorr, B., and Schwartz, R., “A Lexically-Driven Algorithm for Disfluency Detection”, Proc. HLT/NAACL, pp. 157-160, 2004.
[31] Yuan Zhao and Dan Jurafsky, “A preliminary study of Mandarin filled pauses”, Proceedings of DiSS’05, Disfluency in Spontaneous Speech Workshop.
[32] The Stanford Parser: A statistical parser http://nlp.stanford.edu/software/lex-parser.shtml
[33]Hua WU and Ming ZHOU, “Synonymous Collocation Extraction Using Translation Information”, Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, page 120-127, 2003
[34]Diana Inkpen, “A statistical model for near-synonym choice” ACM Transactions on Speech and Language Processing (TSLP) Vol.4 Issue 1, 2007
[35] Hua Wu and Ming Zhou, “Optimizing synonym extraction using monolingual and bilingual resources” Proceedings of the second international workshop on Paraphrasing – Vol.16, Page 72-79, 2003
[36]Keh-Jiann Chen and Jia-Ming You, “A Study on Word Similarity using Context Vector Models” Computational Linguistics and Chinese Language Processing, Vol.7 No.2 Page 37-58, 2002
[37] Turney, P., Littman, M.L., Bigham, J., Shnayder and V. Source, “Combining Independent Modules to Solve Multiple-Choice Synonym and Analogy Problems”, Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP-03), 482-489
[38]Thomas K. Landauer and Susan T. Dumais, “A Solution to Plato’s Problem: The Latent Semantic Analysis Theory of Acquisition, Induction and Representation of Knowledge.” Psychological Review, 104(2):211-240, 1997
[39] Agrawal R, Imielinski T, Swami AN. "Mining Association Rules between Sets of Items in Large Databases." SIGMOD. June 1993, 22(2):207-16
[40] R. Agrawal and R. Srikant, “Fast algorithms for mining association rules in large database.” Technical Report FJ9839, IBM Almaden Research Center, San Jose, CA, Jun. 1994.
[41] Mei, Gia-Chu et al., 同義詞詞林(Cilin-thesaurus of Chinese words). Hong Kong, 商務印書館香港分館.
[42] 赵妍妍, 秦兵, 刘挺, 张俐, 苏中, “基于多特征融合的句子相似度计算,” 全 国第八届计算语言学联合学术会议 (JSCL-2005). 2005年8月, 南京, pp168-174