Full-Text PDF    Submission   Back

Abstract
Some problems on Algorithmic Composition are discussed, and a survey for series of key techniques used in this approach is made, which include Markov chains, stochastic process, musical knowledge based system, musical grammar, artificial neural networks, and genetic algorithms. The conclusion is that the development of music composition system should involve a combination of the existing technologies, i.e. the Hybrid System development. In order to make the system become more practical and effective, there should be some flexible human intervenient ways for different level music composition in the system.

Feng Y, Zhou CL. Advances in algorithmic composition. Journal of Software, 2006,17(2): 209-215. 
DOI: 10.1360/jos170209
http://www.jos.org.cn/1000-9825/17/209.htm


摘要
讨论了当今算法作曲这一研究领域中存在的一些主要问题.评述了这一领域所采用的一系列关键技术,包括Markov链、随机过程、基于音乐规则的知识库系统、音乐文法、人工神经网络技术以及遗传算法.得出的结论是,作曲系统可以朝着集多种方法为一体的混合型系统(hybrid system)的方向发展.系统应在音乐创作的各个层面上提供灵活的人机交互手段,以便提高系统的实用性和有效性.

基金项目：Supported by the National Natural Science Foundation of China under Grant Nos.60275023, 60373080 (国家自然科学基金); the Natural Science Foundation of Fujian Province of China under Grant No.A0210005 (福建省自然科学基金); the Science and Research Start-Up Project for the Recruit Talent of Xiamen University of China under Grant No.E43014 (厦门大学引进人才科研启动费)

References: 

[1] Alpen A. Techniques for algorithmic composition of music. 1995. http://alum.hampshire.edu/~adaF92/algocomp/algocomp95.html

[2] Grout DJ. History of Western Music. 5th ed., New York: W. W. Norton & Company, 1996.

[3] J?rvelainen H. Algorithmic musical composition. 2000. http://www.tml.tkk.fi/Studies/Tik-111.080/2000/papers/hanna/alco.pdf

[4] Cope D. Virtual Music: Computer Synthesis of Musical Style. Cambridge: MIT Press, 2001.

[5] Cope D. MP3 Files of David Cope and Experiments in Musical Intelligence. 2005. http://arts.ucsc.edu/faculty/cope/mp3page.html

[6] Jacob BJ. Algorithmic composition as a model of creativity. Organised Sound, 1996,1(3):157?165

[7] Leman M. Artificial neural networks in music research. In: Marsden A, Pople A, eds. Computer Representations and Models in Music. London: Academic Press, 1992. 265?301.

[8] Toiviainen P. Symbolic AI versus connectionism in music research. In: Miranda E, ed. Readings in Music and Artificial Intelligence. Amsterdam: Harwood Academic Publishers, 2000. 47?67.

[9] Basset BA, Neto JJ. A stochastic musical composer based on adaptive algorithms. 1999. http://gsd.ime.usp.br/sbcm/1999/papers/Bruno_Basseto.pdf

[10] Bartetzki A. CMask, a stochastic event generator for Csound. 1997. http://gnom.kgw.tu-berlin.de/~abart/CMaskMan/CMask-Manual.htm

[11] Lewis JP. Creation by refinement and problem of algorithmic music composition. In: Todd PM, Loy DG, eds. Music and Connectionism. Cambridge: MIT Press/Bradford Books, 1991. 212?228.

[12] Capanna A. Iannis xenakis?Architect of light and sound. Nexus Network Journal, 2001,3(2). http://www.nexusjournal.com/Capanna-en.html

[13] Ames C, Domino M. Cybernetic composer: an overview. In: Balaban M, Ebcioglu K, Laske O, eds. Understanding Music with AI. Cambridge: AAAI Press, 1992. 186?205.

[14] Walker E. Chaos melody theory. 2001. http://www.ziaspace.com/elaine/chaos/ChaosMelodyTheory.pdf

[15] Ebcioglu K. An expert system for harmonizing chorales in the style of J. S. Bach. In: Balaban M, Ebcioglu K, Laske O, eds. Understanding Music with AI. Cambridge: AAAI Press, 1992. 294?334.

[16] Steedman M. The blues and abstract truth: Music and mental models. In: Garnham A, Oakhill J, eds. Mental Models in Cognitive Science. Erlbaum, 1996. 305?327.

[17] Todd PM, Loy G. Music and Connectionism. Cambridge: MIT Press, 1991.

[18] Griffith N, Todd PM. Musical Networks. Cambridge: MIT Press, 1997.

[19] Mozer MC. Neural network composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Cognitive Science, 1994,6:247?280.

[20] Hochreiter S, Schmidhuber J. Long short-term memory. 1996. http://citeseer.ist.psu.edu/hochreiter96long.html

[21] Gers FA, Schmidhuber J. LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Trans. on Neural Networks, 2001,12(6):1333?1340.

[22] Eck D. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In: Boulard H, ed. Neural Networks for Signal Processing XII, Proc. of the 2002 IEEE Workshop. New York: IEEE, 2002. 747?756.

[23] Wiggins G, Papadopoulos G, Phon-Amnuaisuk S, Tuson A. Evolutionary methods for musical composition. 1998. http://citeseer.ist.psu.edu/wiggins98evolutionary.html

[24] Biles JA. Genjam: A genetic algorithm for generating jazz solos. In: Proc. of the Int'l Computer Music Conf. San Francisco: ICMA, 1994. 131?137.

[25] Biles JA. GenJam in transition: From genetic jammer to generative jammer. 2002. http://www.generativeart.com/papersGA2002/8.pdf

[26] Unemi T. A tool for multi-part music composition by simulated breeding. In: Gedau A, ed. Artificial Life VIII. Cambridge: MIT Press, 2002. 410?413.

[27] Unehara M, Onisawa T. Construction of music composition system with interactive genetic algorithm. 2003. http://www.idemployee.id.tue.nl/g.w.m.rauterberg/conferences/CD_doNotOpen/ADC/final_paper/549.pdf

[28] Biles JA. Autonomous genJam: Eliminating the fitness bottleneck by eliminating fitness. 2002. http://www.cs.usyd.edu.au/~josiah/gecco_workshop_biles.pdf

[29] Chen CCJ, Miikkulainen R. Creating melodies with evolving recurrent neural networks. 2001. http://www.cs.utexas.edu/users/nn/downloads/papers/chen.ijcnn01.pdf

[30] Johnson R, Cope D. Computer and musical style. 1991. http://csml.som.ohio-state.edu/Music839C/Notes/Cope.html