臺灣博碩士論文加值系統

現今，行動多媒體播放器被廣泛的使用，如：智慧型手機、平板電腦……等等，讓數位音樂的需求量大增，對於音樂資料庫的應用也更加熱門。音樂資料的內容可以提供多樣的特徵，以用來作為分類或查詢的參考依據，例如：主旋律、節拍與和弦等等，都可以用來呈現每一首音樂獨特的曲風與特性。因此，以內容為主的音樂擷取，多年來一直都是音樂資料庫研究的重要方向，在相關研究的議題有音樂的分類、特徵擷取、(多)特徵索引或近似搜尋等等，都是為了幫助使用者可以快速找到所需要的音樂。
此外，音樂治療是利用音樂來幫助病人改善他們身心靈的健康。當人們放鬆閉眼休息的時候，人的腦部訊號會產生一種頻率介於8~14Hz間的α波。許多的醫學相關研究報告指出，有一些特定的音樂可以與人腦的α波產生共振，並增強此波的產生。如此，這些α波音樂可以幫助人們更加的放鬆紓壓，當人們需要休息時，將可以有很大的幫助。這也就是為什麼人們在放鬆或紓壓時，經常喜歡聽著音樂的緣故。目前對這些α波音樂的分類，都是靠專家做人工辨別。雖然也已經有許多的音樂分類研究被發表，但多是依音樂的風格與流派在分類，例如：搖滾、古典、爵士、鄉村等等。
至今還沒有對α波音樂的分類方法研究被提出來。這個研究報告，我們將探討如何對α波音樂做分析。 期望我們的研究成果，能幫助發展音樂分類系統更為擴大應用與實用可行，以及希望能對音樂治療方面也有所助益。

Since portable devices and digital audio players (ex. iPad, iPod, iPhone, Smartphone, etc.) become more and more popular, the essential of digital music also becomes urgent. It brings on the applications of music database in great demand. The content of digital music provides many features which can be used for music analysis and retrieval. The music features, such as melody, rhythm, chord, and so on, can represent the music styles and characteristics. Therefore, content-based music retrieval is an important research field for music databases. The related researches consist of music classification, music feature extraction, music indexing, approximate music searching and so forth which are all used for users to easily and quickly search the target in a music database.
Furthermore, music therapy uses music to help patients to improve or maintain their physical and spiritual health. When people relax with closed eyes, an alpha wave in the frequency range of 8–12Hz appears with brain signals. There were many medical reports proofed that some specific music can resonate with the alpha wave. Therefore, these alpha wave music can improve more relaxing for people and is very helpful when they need to take a rest. That's why people like to listen music when relaxing. Currently, these of specific music are classified manually by expertise only. The existing music classification approaches are almost all categorized by styles and genres, such as pop, classical, jazz, folk, etc. Accordingly, till now, there is no research report studied about classification of alpha wave music. In this research, we will investigate the content-based features of the alpha wave music, and develop the classification method for alpha wave music. We expect our effort can help to expand the applications and develop the more realistic of music classification system as well as to aid music therapy.

摘要 I
Abstract III
目錄 V
圖目錄 VII
表目錄 VIII
第一章 前言 1
第二章 文獻探討 8
2.1 SRP-Based Classification 8
2.2 Hierarchical Genre Classification 9
2.3 Content-Based Multi-Feature Music Classification 10
2.4 Extreme Learning Machine, ELM 10
2.5 Chord Recognition 11
2.6 Multi-modal Music Genre Classification 12
2.7 Mulit-Label Music Mood Classification 12
第三章 研究方法 14
3.1 音樂特徵 14
3.2 分類方法 16
第四章實驗分析 18
4.1 實驗設定 18
4.2 旋律音符之分析分類法 19
4.3 節拍之分析分類法 20
4.4 前後音差之分析分類法 22
4.5 前後音差之反證分析 23
第五章 結論與未來研究方向 27
參考文獻 29
圖目錄
圖1. EEG 檢測β 波1 秒鐘頻率樣本[44] ....................................................... 2
圖2. EEG 檢測α 波1 秒鐘頻率樣本[45] ....................................................... 3
圖3. EEG 檢測θ 波1 秒鐘頻率樣本[46] ....................................................... 3
圖4. EEG 檢測δ 波1 秒鐘頻率樣本[47] ....................................................... 4
圖5. 以音符分析之分類百分比 .................................................................... 20
圖6. 以節拍分析之分類百分比 .................................................................... 21
圖7. 以前後音差分析之分類百分比 ............................................................. 23
圖8. Classic 以前後音差分類結果 ................................................................. 24
圖9. Pop 以前後音差分類結果 ...................................................................... 25
圖10. Folk 以前後音差分類結果 ................................................................... 26
圖11. jazz 以前後音差分類結果 .................................................................... 26
表目錄
表1. 各類音樂之音符發生頻率最高前7 名統計 ......................................... 20
表2. 各類音樂之節拍發生頻率最高前7 名統計 ......................................... 21
表3. 各類音樂之前後音差發生頻率最高前7 名統計 ................................. 23
表4. Classic 以前後音差分類結果 ................................................................. 24
表5. Pop 以前後音差分類結果 ...................................................................... 25
表6. Folk 以前後音差分類結果 ..................................................................... 25
表7. Jazz 以前後音差分類結果 ..................................................................... 26

[1]C. Anagnostopoulou and G. Westermann(1997), “Classification in Music: A Computational Model for Paradigmatic Analysis,” Proceedings of the International Computer Music Conference.
[2]S. Andrews, I. Tsochantaridis, and T. Hofmann(2003), “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.
[3]H. Berger (Author), P. Gloor (Editor) (1969), On the Electroencephalogram of Man (Electroencephalography and Clinical Neurophysiology Supplement No. 28), Elsevier Science Ltd, ISBN-10: 0444407391.
[4]E. Basar(1980), EEG Brain Dynamics, Elsevier Science, Amsterdam.
[5]E. Basar(1988), Dynamics of Sensory and Cognitive Processing by the Brain, Springer Verlag, Berlin, Germany.
[6]S. G. Blackburn and D. C. DeRoure(1998), “A Tool for Content-based Navigation of Music,” Proceedings of the ACM Multimedia, pp.361-368.
[7]S. Brecheisen, H.-P. Kriegel, P. Kunath, and A. Pryakhin(2006), “Hierarchical Genre Classification for Large Music Collections” IEEE 7th international conference on multimedia and Expo, pp. 1385-1388.
[8]B.S. Bhattacharya, D. Coyle, and L. Maguire(2010), “Thalamocortical circuitry and alpha rhythm slowing: An empirical study based on a classic computational model,” the 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1-7,18-23.
[9]W. Chai and B. Vercoe(2001), “Folk Music Classification Using Hidden Markov Models,” Proceedings of International Conference on Artificial Intelligence.
[10]Y. Chen, J. Bi, and J. Z. Wang(2006), “MILES: Multiple-instance learning via embedded instance selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No.12, pp. 1931-1947.
[11]H. T. Cheng, Y. H. Yang, Y. C. Lin, and H. H. Chen(2008), “Automatic Chord Recognition for Music Classification and Retrieval,” IEEE International Conference on Multimedia and Expo, pp. 1505-1508.
[12]G. Davenport, T. A. Smith, and N. Pincever(1991), “Cinematic Primitives for Multimedia,” IEEE Computer Graphics & Applications, Vol. 11, No. 4, pp. 67-74.
[13]Y. F. Day, S. Pagtas, M. Iino, A. Khokhar, and A. Ghafoor(1995), “Objcet-Oriented Conceptual Modeling of Video Data,” Proceedings of the IEEE Data Engineering, pp. 401-408.
[14]R. B. Dannenberg, B. Thom, and D. Watson(1997), “A Machine Learning Approach to Musical Style Recognition,” Proceedings of International Computer Music Conference.
[15]E. A. E1-Kwae and M. R. Kabuka(2000), “Efficient Content-Based Indexing of Large Image Databases,” ACM Transaction on Information Systems, Vol. 18, No. 2, pp. 171-210.
[16]A, Gevins, A. Rémond, (Eds.)(1987), Handbook of EEG and Clinical Neurophysiology, Vol. 1: Methods of analysis of brain electrical and magnetic signals, Elsevier Science, Amsterdam, Holland.
[17]Z. Fu, G. Lu, K. M. Ting and D. Zhang(2010), “Learning Naive Bayes Classifiers for Music Classification and Retrieval,” 20th International Conference on Pattern Recognition (ICPR), pp. 4589-4592.
[18]Z. Fu, G. Lu, K. M. Ting and D. Zhang(2011), “A Survey of Audio-based Music Classification and Annotation,” IEEE Transactions on Multimedia, Vol. 13, No. 2, pp. 303-319.
[19]S. T. Goh and K. L. Tan(2000), “MOSAIC: A Fast Multi-Feature Image Retrieval System,” Data & Knowledge Engineering, Vol. 33, No. 3, pp.219-239.
[20]K. D. Goodman(2011), Music Therapy Education and Training: From Theory to Practice, Springfield, Illinois: Charles C. Thomas., ISBN 0-398-08609-5 .
[21]R. Hjelsvold, and R. Midstraum(1994), “Modeling and Querying Video Data,” Proceedings of the International Conference on VLDB, pp. 686-694.
[22]K. A. Hua, K. Vu, and J. H. Oh(1999), “SamMatch: A Flexible and Efficient Sampling-Based Image Retrieval Technique for Large Image Databases,” Proceedings of the ACM Multimedia, pp. 225-234.
[23]X. Huang, A. Acero, and H.-W. Hon(2001), Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Prentice Hall.
[24]C. L. Krumhansl(1990), Cognitive Foundations of Musical Pitch, Oxford University Press, New York.
[25]C. C. Liu, J. L. Hsu, and Arbee L. P. Chen(1999), “Efficient Theme and Non-Trivial Repeating Pattern Discovering in Music Databases,” Proceedings of the IEEE Data Engineering, pp.14-21.
[26]C-R. Lin, N-H. Liu, Y-H. Wu, and A. L. P. Chen(2004), “Music Classification Using Significant Repeating Patterns,” Lecture Notes in Computer Science, Springer-Verlag, Vol. 2973, pp. 506-518.

[27]Q. J. B. Loh, and S. Emmanuel(2006), “ELM the Classification of Music Genres,” ICARCV’06. 9th International conference on Control, Automation, Robotics and Vision, pp. 1-6.
[28]Y. L. Lo, W. L. Lee, and L. H. Chang(2008), “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.
[29]Y. L. Lo and L. Y. Tsai(2009) , “Approximate Searching for Music Data in Real-Valued Feature Indexing,” Journal of Convergence Information Technology, Vol. 4, No. 4, pp. 87-95.
[30]Y. L. Lo, C. H. Lee, and C. H. Wang(2009), “Scalable Multi-feature Index Structure for Music Databases,” Information Sciences, Elsevier, Vol.179, No 15, pp. 2662-2675.
[31]Y. L. Lo and Y. C. Lin(2010), “Content-Based Music Classification,” the 3rd IEEE International Conference on Computer Science and Information Technology , Chengdu, China, pp. 112-116 .
[32]Y. L. Lo and Y. C. Lin(2012), “Content-Based Multi-Feature Music Classification,” International Conference on Innovation and Management (IAM2012), Republic of Palau.
[33]I. Mandel, and P. W. Ellis(2008), “Multiple-Instance Learning for Music Information Retrieval,” 9th International Conference on Music Information Retrieval, pp.577-582.
[34]E. E. P. Myint and M. Pwint(2010), “An Approach for Mulit-label Music Mood Classification,” 2nd International Conference on Signal Processing Systems (ICSPS), pp. V1-290 - V1-294.
[35]E. Narmour(1990), The Analysis and Cognition of Basic Melodic Structures, The University of Chicago Press, Chicago.
[36]S. Nepal and M. V. Ramakrishna(1999), “Query Processing Issue in Image (Multimedia) Databases,” Proceedings of the International Conference on Data Engineering, pp.22-29.
[37]J. H. Oh and K. A. Hua(2000), “Efficient and Cost-Effective Techniques for Browsing and Indexing Large Video Databases,” Proceedings of the ACM SIGMOD, pp.415-426.
[38]S. W. Smoliar and H. J. Zhang(1994), “Content-Based Video Indexing and Retrieval,” IEEE Multimedia, Vol. 2, No. 1, pp. 63-75.
[39]V. N. Vapnik(1995), The Nature of Statistic Learning Theory, New York, Springer-Verlag.
[40]K. Vijayalakshmi, S. Sridhar, and P. Khanwani(2010), “Estimation of effects of alpha music on EEG components by time and frequency domain analysis,” International Conference on Computer and Communication Engineering (ICCCE), Kuala Lumpur, Malaysia, pp. 1-5, 11-13.
[41]S. Vakili, N. Tehranchian, M. Tajziehchi, and I.M. Rezazadeh, and Xiangyu Wang(2012), “An empirical study on the relations between EEG alpha-beta entropy & EQ- IQ test scores,”2012 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), pp. 301-304.
[42]C. Zhen and J. Xu(2010), “Multi-modal Music Genre Classification Approach,” 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT), pp. 398-402.
[43]羅有隆、林奕昌(2011)，「以多特徵分析為基礎之音樂資料分類」，資訊科技國際期刊，Vol 5,No 1，pp.146-157。
[44]H. Gamboa(2005), “Beta Wave”, Wikipedia. http://en.wikipedia.org/wiki/Beta_wave
[45]H. Gamboa(2005), “Alpha Wave”, Wikipedia. http://en.wikipedia.org/wiki/Alpha_wave
[46]H. Gamboa(2005), “Theta Wave”, Wikipedia. http://en.wikipedia.org/wiki/Theta_wave
[47]H. Gamboa(2005), “Delta Wave”, Wikipedia. http://en.wikipedia.org/wiki/Delta_wave
[48]α波 童話音樂盒系列--宮崎駿動畫名曲集 http://www.books.com.tw/exep/cdfile.php?item=0020127497
[49]α波 童話音樂盒系列--迪士尼動畫名曲集1 http://www.books.com.tw/exep/cdfile.php?item=0020127496
[50]α波 童話音樂盒系列--迪士尼動畫名曲集2 http://www.books.com.tw/exep/cdfile.php?item=0020127498
[51]α腦波音樂對不同人群的超強幫助 http://hdmok0909.pixnet.net/blog/post/9195968-α腦波音樂對不同人群的超強幫助
[52]巴洛克音樂每分鐘60拍-和人腦放鬆而清醒時的a波頻率同步 http://bbs.gsr.org.tw/cgi-bin/printpage.cgi?forum=6&topic=50