現階段的鋼琴音樂教育，教師對於同一首音樂情緒有著不同的主觀意識，這讓學生在學習時容易產生困難與困惑。 本論文建構一個即時線上輔助鋼琴學習系統，記錄並分析學習者鋼琴彈奏內容的音樂特徵，再利用機器學習的技術，以決策樹之方式建構教師專業分類彈奏音樂情緒的法則，並提供視覺化的學習界面，讓學生可以在任意時間透過電腦選擇不同教師線上建構好的教材，將自己彈奏錄製好的數位鋼琴音樂輸入情感分析模組，便能快速了解彈奏是否達到不同教師主觀上的要求，以學習不同音樂情緒的彈奏技巧。

This paper proposed a machine learning approach for analyzing teachers’ expert knowledge of classifying students’ piano performance into approximate expression categories. In traditional piano learning environment, students are usually confused when learning the expressive performance because of teachers’ subjective intention difference on the same performance. In this thesis, teacher models were built by analyzing teachers’ classification rules. By replaying students’ performances and read teachers’ suggestions in graphical and textual modes which are generated automatically by the teacher model, students could understand the nuance of performance features on each expression. Nine teachers and ten students joined this experiment. Forty six piano performances were recorded for constructing the teacher model. The average accuracy of teacher model for classifying performance expression is 89.1%. It only takes 9.84 seconds to build the teacher model and 0.1 second to automatically classify each recorded performance. This thesis proposed a highly accurate and fast-processing-rate analyzing system to assist teaching and help students understanding musical expression.

1. 鄭敬譯, 私立技術學院數位學習導入之研究. 生活科技教育月刊, 2004. 37(5): p. 7-14.
2. Levi, D.S., Expressive Qualities in Music Perception and Music Education. Journal of Research in Music Education, 1978. 26(4): p. 425-435.
3. 王曉璿, 資訊科技融入音樂科教學探究. 中學教育學報第八期, 2001: p. p97-121.
4. 蔡辰男, 學習音樂百科全書4. 1981, 台北: 百科文化.
5. Fritz, T., Universal Recognition of Three Basic Emotions in Music. Current Biology, 2009. 19(7): p. 573-576.
6. 吳相妤, 盧塞爾《吹笛人，作品二十七》之作品研究與詮釋探討. 2000, 台北: 東吳大學碩士論文.
7. Palmer, C., Mapping musical thought to musical performance. Journal of experimental psychology. Human perception and performance, 1989. 15.
8. Kendall, R.A. and E.C. Carterette, Communicating performer intent through musical performance. I. Mapping intent to perception. The Journal of the Acoustical Society of America, 1996. 100(4): p. 2777-2777.
9. Minetti, A.E., L.P. Ardigo, and T. McKee, Keystroke dynamics and timing: Accuracy, precision and difference between hands in pianist's performance. Journal of Biomechanics, 2007. 40(16): p. 3738-3743.
10. Honing, H., Structure and Interpretation of Rhythm and Timing. Dutch Journal of Music Theory, 2002. 7(3): p. 227-232.
11. Canazza, S., G. De Poli, and A. Vidolin, Perceptual analysis of the musical expressive intention in a clarinet performance, in Music, Gestalt, and Computing. 1997. p. 441-450.
12. Köhler, W., Gestalt psychology. 1963, New York: Liveright.
13. Peifeng, X., Y. Xin, and S. Yuanchun. Web Page Segmentation Based on Gestalt Theory. in 2007 IEEE International Conference 2007: Multimedia and Expo.
14. 林朝霞, 音樂: 戴著腳鐐的靈魂之舞-解決情感論與形式論的分歧. 藝術探索, 2008. 22(6): p. 70-71.
15. Cohen, D. and S. Dubnov, Gestalt Phenomena in Musical Texture. Music, Gestalt, and Computing, 1997: p. 386-405.
16. Godøy, R.I., Knowledge in Music Theory by Shapes and Sound-Producing Actions. Music, Gestalt, and Computing, 1997: p. 89-102.
17. Witten, I.H. and E. Frank, Data Mining: Practical Machine Learning Tools and Techniques (Second Edition). 2005, San Francisco: Morgan Kaufmann.
18. Mitchell, T., Machine Learning. 2006, New York: McGraw Hill.
19. 田宜歆, 輔助教師以機器學習分析及評量學生鋼琴演奏技巧之研究 2008.
20. Feigenbaum, R.A. The art of artificial intelligence: I. Themes and case studies of knowledge engineering. in Proc. of the 5th IJCAI. 1977.
21. Quinlan, J.R., Induction of Decision Trees. Mach Learn, 1986. 1(1): p. 81-106.