Dear list,
Dimitris posed the question of whether there are any publications on the topic of algorithmic music generation in a human-societal context. Below I've pasted an abridged version of my own bibliography for algorithmic music generation, and I think the first few items could provide interesting starting points and reference other works that speak to Dimitris' question (e.g., Boden's The Creative Mind, cited by Wiggins, 2006).
One issue still faced by the field of algorithmic music generation is lack of rigorous evaluation by human listeners. Evaluation by humans listeners would to some extent close the loop to which Dimitris refers (to paraphrase, "music composed by humans, for humans"). Still too often, researchers X apply some computational method to music data in order to generate passages, write a journal or conference paper about their method, and conclude glibly that the passages "sound convincing" or "are pleasant to listen to". Pearce et al. (2002) address this topic, and there are examples in among the papers below of how evaluations ought to be being conducted (Pearce & Wiggins, 2007; Collins et al., 2016).
Please feel free to contact me off list if you are struggling to get one of the papers.
All best,
Tom
Wiggins, Geraint A. (2006). A preliminary framework for description, analysis and comparison of creative systems. Knowledge-Based Systems, 19(7):449-458.
Pearce, Marcus, Meredith, David, and Wiggins, Geraint A. (2002). Motivations and methodologies for automation of the compositional process. Musicae Scientiae, 6(2):119-147.
Collins, Tom, Laney, Robin, Willis, Alistair and Garthwaite, Paul H. (2016). Developing and evaluating computational models of musical style. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 30(1):16-43. Accepted version:
Wiggins, Geraint A. (2008). Computer models of musical creativity: a review of computer models of musical creativity by David Cope. Literary and Linguistic Computing 23(1):109-115.
Cope, David, Computer models of musical creativity. (2005). Cambridge, MA: MIT Press.
Nierhaus, Gerhard. (2009). Algorithmic composition: paradigms of automated music generation. Vienna: Springer-Verlag.
Pearce, Marcus., and Wiggins, Geraint A. (2007). Evaluating cognitive models of musical composition. Proceedings of the Fourth International Joint Workshop on Computational Creativity (pp. 73-80), Goldsmiths, University of London.
Allan, Moray. (2002). Harmonising chorales in the style of Johann Sebastian Bach. Master's thesis, School of Informatics, University of Edinburgh. Downloaded from
http://www.tardis.ed.ac.uk/~moray on 9 November 2009.
Hedges, Thomas, Roy, Pierre, and Pachet, Francois. (2014). Predicting the composer and style of jazz chord progressions. Journal of New Music Research 43(3): 276-290.
Cherla, S., T. Weyde, , A. d'Avila Garcez, and M.T. Pearce. (2013). A distributed model for multiple-viewpoint melodic prediction. Proceedings of the International Symposium on Music Information Retrieval (pp. 15-20), Curitiba, Brazil.
Gonzalez Thomas, N., Pasquier, P., Eigenfeldt, A., and Maxwell, J.B. (2013). Meta-Melo: a system and methodology for the comparison of melodic generation models. Proceedings of the International Symposium on Music Information Retrieval (pp. 561-566), Curitiba, Brazil.
Pachet, Francois, and Roy, Pierre. (2011). Markov constraints: steerable generation of Markov sequences, in Constraints, 16(2):148-172.
Pachet, Francois. (2002). Interacting with a musical learning system: the continuator. Proceedings of the International Conference on Music and Artificial Intelligence (pp. 119-132), Lecture Notes in Artificial Intelligence. Berlin: Springer-Verlag.
Pachet, Francois, and Roy, Pierre. (2014). Non-conformant harmonization: the Real Book
in the style of Take 6. Proceedings of the International Conference on Computational Creativity. Ljubljana, Slovenia.
Roy, Pierre, and Pachet, Francois. (2014). Enforcing meter in finite-length Markov sequences. Proceedings of the AAAI Conference on Artificial Intelligence (pp. 1–8). Bellevue, WA: Association for the Advancement of Artificial Intelligence.
Tom Collins, PhD
Early Career Research Fellow
Faculty of Technology
De Montfort University
Leicester, UK