臺灣博碩士論文加值系統

已被發展出的音樂分類技術可概分為兩個方向，其一為以學習機器為訓練基礎的分類方式，另一則為以音樂內容為基礎的分析分類方式，各有其優缺點。而其中，現有以音樂內容為基礎的分類方式，多以音樂之單特徵進行，在少數類型的音樂辨識可達70%左右的分類精確度，而多數類型的音樂，可正確被分類的精確度則低了許多。本研究報告在於分析與研究音樂資料內容，並利用音樂資料的多特徵性質，找出是否有每一類型音樂所特有的內容特徵，並以這些特徵設計出具更高精確度的音樂資料分類公式。在我們的實驗中，我們發現利用音樂內容之多重特徵為分類基礎，可讓鄉村音樂、古典音樂、流行音樂與爵士音樂，分別達到85%、82%、80%與73%的分類精確度。

The music classification techniques can be discriminated into two categories — based by music feature classification and training by learning machine classification. Both have their advantages and disadvantages. For music feature classifications, most of the approaches are based on single music feature, such as melody or chord, and the accuracy is about 70% in few genres of music. However, the accuracy for classification of most music genres is lower. In this research, we study the music contents and use the multi-features of music to design equation for more accuracy music classification. Our performance study shown that more than 85%, 82%, 80%, and 73% of folk, classic, pop, and jazz music can be classified correctly, respectively, by using multi-feature of music content for classification.

目錄
摘要. I
Abstract II
誌謝. III
目錄. Ⅳ
表目錄. Ⅵ
圖目錄.. Ⅶ
第一章 導論 1
第二章 文獻探討 4
2.1 SRP-Based Classification 4
2.2 Hierarchical Genre Classification 5
2.3 Extreme Learning Machine, ELM 6
2.4 Multiple-Instance Learning 6
2.5 Chord Recognition 7
第三章 音樂分類公式設計 8
第四章 精確度分析 12
4.1 單特徵分類的分析 13
4.1.1單特徵正向分析對分類的影響 13
4.1.2單特徵逆向分析對分類的影響 22
4.2 多特徵對分類的分析 29
4.2.1多特徵正向分析對分類的影響 29
4.2.2多特徵逆向分析對分類的影響 32
第五章 結論與未來展望 36
參考文獻 38

表目錄
表 1、古典音樂音符出現頻率前七名 14
表 2、單特徵-音符正向分析半徑與圓心座標(比率90%與k=2) 17
表 3、各音樂類型單特徵音符正向分析半徑與精確度(k=5) 18
表 4、各音樂類型單特徵節拍正向分析半徑與精確度(k=5) 20
表 5、各音樂類型單特徵前後音差正向分析半徑與精確度(k=5) 22
表 6、流行音樂音符出現頻率最後七名 23
表 7、各音樂類型單特徵音符逆向分析半徑與精確度(k=5) 26
表 8、各音樂類型單特徵節拍逆向分析半徑與精確度(k=5) 27
表 9、各音樂類型單特徵前後音差逆向分析半徑與精確度(k=5) 29
表 10、各音樂類型分類特徵與精確度 36

圖目錄
圖 1、古典音樂音符分布圖 14
圖 2、以音符特徵值正向分析分類之精確度 16
圖 3、單特徵-音符正向分析 (k=2)二維圓心圖 17
圖 4、以節拍特徵值正向分析分類之精確度 19
圖 5、以前後音差特徵值正向分析分類之精確度 21
圖 6、流行音樂音符分布圖 23
圖 7、以音符特徵值逆向分析分類之精確度 25
圖 8、以節拍特徵值逆向分析分類之精確度 27
圖 9、以前後音差特徵值逆向分析分類之精確度 28
圖 10、以音符+節拍特徵值數目正向分析分類之精確度 30
圖 11、以音符+前後音差特徵值數目正向分析分類之精確度 30
圖 12、以節拍+前後音差特徵值數目正向分析分類之精確度 31
圖 13、以音符+節拍+前後音差特徵值數目正向分析分類之精確 31
圖 14、以音符+節拍特徵值數目逆向分析分類之精確度 33
圖 15、以音符+前後音差特徵值數目逆向分析分類之精確度 33
圖 16、以節拍+前後音差特徵值數目逆向分析分類之精確度 34
圖 17、以音符+節拍+前後音差特徵值數目逆向分析分類之精確 34

[1]C. Anagnostopoulou and G. Westermann, “Classification in Music: A Computational Model for Paradigmatic Analysis,” Proceedings of the International Computer Music Conference, 1997.
[2]S. Andrews, I. Tsochantaridis, and T. Hofmann, “Support vector machines for multiple-instance learning,” In S. Thrun and K. Obermayer, editors, Advances in Neural Information Processing Systems 15, pages 561-568, MIT Press, Cambridg, MA, 2003.
[3]S. G. Blackburn and D. C. DeRoure, “A Tool for Content-based Navigation of Music,” Proceedings of the ACM Multimedia, pp.361-368, 1998.
[4]S. Brecheisen, H.-P. Kriegel, P. Kunath, and A. Pryakhin, “Hierarchical Genre Classification for Large Music Collections” IEEE Seventh international conference on multimedia and Expo, pp. 1385-1388, 2006.
[5]W. Chai and B. Vercoe, “Folk Music Classification Using Hidden Markov Models,” Proceedings of International Conference on Artificial Intelligence, 2001.
[6]Y. Chen, J. Bi, and J. Z. Wang, “MILES: Multiple-instance learning via embedded instance selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12):1931-1947, 2006.
[7]H. T. Cheng, Y. H. Yang, Y. C. Lin, and H. H. Chen, “Automatic Chord Recognition for Music Classification and Retrieval,” IEEE International Conference on Multimedia and Expo, pp. 1505-1508, 2008.
[8]G. Davenport, T. A. Smith, and N. Pincever, “Cinematic Primitives for Multimedia,” IEEE Computer Graphics & Applications, Vol. 11, No. 4, pp. 67-74, 1991.
[9]Y. F. Day, S. Pagtas, M. Iino, A. Khokhar, and A. Ghafoor, “Objcet-Oriented Conceptual Modeling of Video Data,” Proceedings of the IEEE Data Engineering,” pp. 401-408, 1995.
[10]R. B. Dannenberg, B. Thom, and D. Watson, “A Machine Learning Approach to Musical Style Recognition,” Proceedings of International Computer Music Conference, 1997.
[11]P. Dhanalakshmi, S. Palanivel, and V. Ramalingam, “Classification of Audio Signals Using SVM and RBFNN” An International Journal Expert Systems with Application, Vol. 36, No. 3, pp. 6069-6075, 2009.
[12]E. A. E1-Kwae and M. R. Kabuka, “Efficient Content-Based Indexing of Large Image Databases,” ACM Transaction on Information Systems, Vol. 18, No. 2, pp. 171-210, 2000.
[13]S. T. Goh and K. L. Tan, “MOSAIC: A Fast Multi-Feature Image Retrieval System,” Data & Knowledge Engineering, Vol. 33, No. 3, pp.219-239, 2000.
[14]R. Hjelsvold, and R. Midstraum, “Modeling and Querying Video Data,” Proceedings of the International Conference on VLDB, pp. 686-694, 1994.
[15]K. A. Hua, K. Vu, and J. H. Oh, “SamMatch: A Flexible and Efficient Sampling-Based Image Retrieval Technique for Large Image Databases,” Proceedings of the ACM Multimedia, pp. 225-234, 1999.
[16]X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Prentice Hall, 2001.
[17]A. Holzapfel, and Y. Stylianou, “Rhythmic Similarity of Music Based on Dynamic Periodicity Warping,” IEEE International Conference on Speech and Siqnal Processing, pp. 2217-2220, 2008.
[18]C. L. Krumhansl, CognitiveFoundations of Musical Pitch, Oxford University Press, New York, 1990.
[19]F. F. Kuo and M. K. Shan “Looking for New, Not Known Music Only: Music Retrieval by Melody Style,” International Conference on Digital Libraries, Pages 243 – 251, 2004.
[20]C-R. Lin, N-H. Liu, Y-H. Wu, and A. L. P. Chen, “Music Classification Using Significant Repeating Patterns,” Lecture Notes in Computer Science, Springer-Verlag, Vol. 2973, pp. 506-518, 2004.
[21]C. C. Liu and Arbee L. P. Chen, “3D-List: A Data Structure for Efficent Video Query Processing,” IEEE TKDE, Vol. 14, No. 1, pp. 106-122, 2002.
[22]C. C. Liu, J. L. Hsu, and Arbee L. P. Chen, “Efficient Theme and Non-Trivial Repeating Pattern Discovering in Music Databases,” Proceedings of the IEEE Data Engineering, pp.14-21,1999.
[23]Y. L. Lo, C. H. Lee, and C. H. Wang, "Scalable Multi-feature Index Structure for Music Databases," Information Sciences, Elsevier, Vol.179, Issue 15, pp. 2662-2675, July 2009.
[24]Y. L. Lo, W. L. Lee, and L. H. Chang, "True Suffix Tree Approach for Discovering Non-trivial Repeating Patterns in a Music Object," Journal of Multimedia Tools and Applications, Springer, Vol. 37, No. 2, pp. 169-187, April 2008.
[25]Y. L. Lo and L. Y. Tsai , “Approximate Searching for Music Data in Real-Valued Feature Indexing,” Journal of Convergence Information Technology, Vol. 4, No. 4, pp. 87-95, Dec. 2009.
[26]Yu-lung Lo and Yi-Chang Lin, “Content-Based Music Classification,” the 3rd IEEE International Conference on Computer Science and Information Technology (IEEE ICCSIT 2010), pp. 112-116, July 9-11, 2010.
[27]Q. J. B. Loh, and S. Emmanuel, “ELM the Classification of Music Genres,” ICARCV’06. 9th International conference on Control, Automation, Robotics and Vision, pp. 1-6, 2006.
[28]I. Mandel, and P. W. Ellis, “Multiple-Instance Learning for Music Information Retrieval,” 9th International Conference on Music Information Retrieval, pp.577-582, 2008.
[29]E. Narmour, The Analysis and Cognition of Basic Melodic Structures, The University of Chicago Press, Chicago, 1990.
[30]S. Nepal and M. V. Ramakrishna, “Query Processing Issue in Image (Multimedia) Databases,” Proceedings of the International Conference on Data Engineering, pp.22-29, 1999.
[31]J. H. Oh and K. A. Hua, “Efficient and Cost-Effective Techniques for Browsing and Indexing Large Video Databases,” Proceedings of the ACM SIGMOD, pp.415-426, 2000.
[32]E. Oomoto and K. Tanaka, “OVID: Design and Implementation of a Video-Object Database System,” IEEE TRANSACTION ON Kowledge and Data Engineering, Vol. 4, No. 4, pp. 629-643, 1993.
[33]S. W. Smoliar and H. J. Zhang, “Content-Based Video Indexing and Retrieval,” IEEE Multimedia, Vol. 2, No. 1, pp. 63-75, 1994.
[34]M.-K. Shan, F.-F. Kuo, and M.-F. Chen, “Music Sytle Mining and Classification by Melody,” Proceedings. 2002 IEEE International Conference on Multimedia and Expo, 2002. ICME ''02, pp. 97-100, 2002.
[35]G. Tzanetakis, G. Essl, and P. Cook, “Automatic Musical Genre Classification of Audio Signals,” Proceedings of International Symposium on Music Information Retrieval, Vol. 10, No. 5, pp. 293-302, 2001.
[36]G. Tzanetakis, A. Ermolinskyi, and P. Cook, “Pitch Histograms in Audio and Symbolic Music Information Retrieval,” Proceedings of International Symposium on Music Information Retrieval, Vol.32, No.2, pp. 143-152, 2002.
[37]V. N. Vapnik, The Nature of Statistic Learning Theory, New York, Springer-Verlag, 1995.
[38]B. Whitman and P. Smaragdis, “Combining Musical and Cultural Features for Intelligent Style Detection,” Proceedings of International Symposium on Music Information Retrieval, 2002.
[39]Y. Zhang, and J. Zhou, “A Study on Content-based Music Classification,” IEEE Seventh International Symposium on Signal Processing and Its Applications, Vol. 2, pp.113-116, 2003.