藍調音樂始於十九世紀初，起源於新大陸殖民者的黑奴拓墾區。由於許多非洲黑人被白人抓來美洲作奴隸，他們就藉著工作或閒暇時間以歌唱來減輕肉體與心靈的苦痛。搖滾樂、爵士樂、節奏藍調（R&B）、嘻哈（hip-hop）…等現今我們所熟悉的流行音樂，無一不與藍調有關。它不僅是搖滾樂的先驅，甚至對古典音樂等世界音樂也皆有所衝擊。藍調可說是──「音樂背後的音樂」。
藍調有三個明確的音樂特性，第一：藍調的作曲以藍調音階的形式進行，第二：以屬七和絃形成藍調基底的的特殊合聲形式，第三：運用裝飾音來裝飾音樂旋律。
在本篇論文中，我們建立了一個藍調風格音樂變奏系統。為了讓變奏後的樂曲更符合藍調特性，我們採用了3個變奏步驟：藍調音階的轉換、裝飾音的增加以及屬七和絃的伴奏。在第一個步驟中，我們設計了一個將大調音階轉換到藍調音階的方法。在第二、三步驟中，我們訓練了兩個Hidden Markov Models來觀察與抽取出資料庫中裝飾音和伴奏的特性。在加入裝飾音時，轉至藍調音階的樂曲的每個小節可視為一個觀察的符號序列，Viterbi演算法可用求出產生這個觀察序列的最大機率的狀態（裝飾音）序列，因為最大機率的狀態序列不符合裝飾音的特性，所以我們另外設計一個修正狀態序列的方法。在屬七和絃伴奏時，已加入裝飾音的樂曲已可視為一個觀察的符號序列，同樣以Viterbi演算法來求出每個小節要配的和絃，再分別以兩種分解式和絃：樂理基礎的十五度分解法與統計基礎的和聲分解法來配伴奏。
實驗結果可看出變奏曲的藍調風格程度隨著變奏三步驟的進行而增加，平均有百分之七十四的實驗者認為變奏曲有藍調風格，就第一個將輸入樂曲變奏為藍調風格的音樂系統來說，這樣的實驗數據是令人滿意的。

Blues is a form of American root music, and it has been a major influence on later popular music. It is composed by Blues scale, and uses grace notes to embellish the melody. It is also formed by the dominant 7th chords as the basis.
In this paper, we describe an HMM (Hidden Markov Model) -based variation system for producing Blues style music. To let the varied melody satisfy the characteristics of the Blues music, there are three varying steps implemented in the system, including: Blues scale transformation, grace notes insertion, and dominant 7th chords accompaniment. The experiment results show that the degree of Blues style increases as the proceeding of the three varying steps, and there are 74 percent of experimenters in average considering the varied melody as the Blues style music. To the best of our knowledge, this is the first variation system for producing Blues style music, and the results are satisfactory.

[1]P. Berg, R. Rowe and D. Theriault, “SSP and Sound Description,” Computer Music Journal, 4(3), pp. 25-35.
[2]E. BILOTTA, P. PANTANO and V. TALARICO, “Synthetic Harmonies: An Approach to Musical Semiosis by Means of Cellular Automata,” In Artificial Life VII: Proceedings of the Seventh International Conference, edited by M. Beday et al. MIT Press, 2000.
[3]H.C. Chen and Arbee L.P. Chen, "A Music Recommendation System Based on Music Data Grouping and User Interests," Proc. ACM International Conference on Information and Knowledge Management 2001.
[4]H.C. Chen, C.H. Lin and Arbee L.P. Chen, “Music Segmentation by Rhythmic Features and Melodic Shapes,” IEEE International Conference on Multimedia & Expo (ICME), 2004.
[5]E. Chew, “The Spiral Array: An Algorithm for Determining Key Boundaries,” International Conference on Music and Artificial Intelligence (ICMAI), 2002.
[6]T.C. Chou, Arbee L.P. Chen and C.C. Liu, "Music Databases: Indexing Techniques and Implementation," Proc. IEEE Intl. Workshop on Multimedia Data Base Management Systems, 1996.
[7]A.S. Durey and M.A. Clements. “Melody Spotting Using Hidden Markov Models. In Proceedings of the International Symposium on Music Information Retrieval”, pages 109-117, Bloomington, IN, October 2001.
[8]D. Eck and J. Schmidhuber, “Finding Temporal Structure in Music: Blues Improvisation with LSTM Recurrent Networks,” In H. Bourlard, editor, Neural Networks for Signal Processing XII, Proc. 2002 IEEE Workshop, pages 747-756, New York, 2002.
[9]M. Farbood and B. Schoner, “Analysis and Synthesis of Palestrina-Style Counterpoint Using Markov Chains,” In International Computer Music Conference, 2001.
[10]J. Harnum, “Basic Music Theory: How to Read, Write, and Understand Written Music,“ -- 1st ed.
[11]M. Hirzel and D. Soukup, “The Viterbi Jazz Improvisator,” May 2000.
[12]J.L. Hsu and Arbee L.P. Chen, "Building a Platform for Performance Study of Various Music Information Retrieval Approaches" International Symposium on Music Information Retrieval, pp. 153-161, 2001.
[13]J.L. Hsu, C.C. Liu and Arbee L.P. Chen, "Discovering Nontrivial Repeating Patterns in Music Data" IEEE Transactions on Multimedia, Vol. 3, No. 3, 2001.
[14]J.L. Hsu and Arbee L.P. Chen, "A Qualitative Comparison (Comparative Study) of Various Techniques for Content-based Music Information Retrieval", 2002.
[15]M.H. Jian, C.H. Lin and A.L.P. Chen, "Perceptual Analysis for Music Segmentation," SPIE Storage and Retrieval Methods and Applications for Multimedia, 2004.
[16]H. Jin and H.V. Jagadish, “Indexing Hidden Markov Models for Music Retrieval,” International Symposium on Music Information Retrieval (ISMIR), 2002.
[17]O.E. Laske, “Composition Theory in Koenig’s Project One and Project Two,” Computer Music Journal, 5(4), 1981, pp. 54-65.
[18]R. Lawrence, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition," Proc. IEEE 77, 1989.
[19]C.H. Lee, C.W. Cho, Y.H. Wu and Arbee L. P. Chen "A Novel Representation of Sequence Data based on Structural Information for Effective Music Retrieval," International Conference on Database Systems for Advanced Applications (DASFAA), 2004.
[20]C.R. Lin, N.H. Liu, Y.H. Wu and Arbee L.P. Chen "Music Classification Using Significant Repeating Patterns" International Conference on Database Systems for Advanced Applications (DASFAA), 2004.
[21]C.C. Liu, J.L. Hsu and Arbee L.P. Chen "Efficient Near Neighbor Searching Using Multi-Indexes for Content-Based Multimedia Data Retrieval," Multimedia Tools and Applications, Vol 13, No. 3, pp.236-254. 2001.
[22]N.H. Liu, Y.H. Wu and Arbee L.P. Chen, "Efficient k-NN Search in Polyphonic Music Databases Using a Lower Bounding Mechanism," ACM SIGMM International Workshop on Multimedia Information Retrieval, 2004.
[23]Y. Marom, “Honours Thesis: Improvising Jazz Using Markov Chains,”, The University of Western Australia, 1997.
[24]A. Marsden. Modeling the Perception of Musical Voices. In Alan Marsden and Anthony Pople, editors, Computer Representations and Models in Music, pages 213{251. Academic Press, 1992.
[25]M.C. Mozer, “Neural Network Music Composition by Prediction: Exploring the Benefits of Psychophysical Constraints and Multiscale Processing,” Connection Science, 6, 247-280, 1994.
[26]G. Papadopoulos and G. Wiggins, “A Genetic Algorithm for the Generation of Jazz Melodies,” In STeP’98, Jyv¨askyl¨a, Finland, 1998.
[27]A. Sheh and D. Ellis. “Chord Segmentation and Recognition Using Em-Trained Hidden Markov Models.” In 4th International Symposium on Music Information Retrieval (ISMIR), October 2003.
[28]J. Shifrin, B. Pardo, C. Meek and W.P. Birmingham, “HMM-Based Musical Query Retrieval.” International Conference on Digital Libraries (JCDL), 295-300, 2002.
[29]H.H. Shih, S. Narayanan and C.C.J. Kuo, “An HMM-Based Approach to Humming Transcription,” IEEE International Conference on Multimedia and Expo (ICME), 2002.
[30]L. Smith and R. Medina, “Discovering Themes by Exact Pattern Matching,” International Symposium on Music Information Retrieval, 2001.
[31]B. Thom. Unsupervised Learning and Interactive Jazz/Blues Improvisation. Proceedings of the Seventeenth National Conference on Artificial Intelligence (AAAI-2000), Austin, TX.
[32]A.L. Uitdenbogerd and J. Zobel, “Manipulation of Music For Melody Matching,” Proceedings of the sixth ACM international conference on Multimedia, 1998, Pages 235 – 240.
[33]G. Wiggins, G. Papadopoulos, S. Phon-Amnuaisuk, and A. Tuson, “Evolutionary Methods for Musical Composition,” International Journal of Computing Anticipatory Systems, 1999.
[34]Y. Zhu and M. Kankanhalli, “Music Scale Modeling for Melody Matching,” ACM Multimedia, 2003.
[35http://www.campusprogram.com/reference/en/wikipedia/b/bl/blues.html
[36]http://www.chipin-kaiya.com/JazzForm/Blues/Blues.html
[37]http://www.dolmetsch.com/musictheory25.htm
[38]http://www.jazclass.aust.com/bl1.htm
[39]http://www.jimmychanbluesharp.com.hk/lesson2.htm
[40]http://www.sciencedaily.com/encyclopedia/blues
[41]http://www.zentao.com/guitar/theory/7th-chords.html