DISTRIBUTED GENERATION OF COMPUTER MUSIC IN THE INTERNET OF THINGS

Problem Statement. The paper deals with distributed intelligent multi-agent system for computer music generation. A mathematical model for data extraction from the environment and their application in the music generation process is proposed. Methods. We use Resource Description Framework for representation of timbre data. A special musical programming language Csound is used for subsystem of synthesis and sound processing. Sound generation occurs according to the parameters of compositional model, getting data from the outworld. Results. We propose architecture of a potential distributed system for computer music generation. An example of core sound synthesis is presented. We also propose a method for mapping real world parameters to the plane of compositional model, in an attempt to imitate elements and aspects of creative inspiration. Music generation system has been represented as an artifact in the Central Museum of Communication n.a. A.S. Popov in the framework of «Night of Museums» action. In the course of public experiment it was stated that, in the whole, the system tends to a quick settling of neutral state with no musical events generation. This proves the necessity of algorithms design for active condition support of agents’ network, in the whole. Practical Relevance. Realization of the proposed system will give the possibility for creation of a technological platform for a whole new class of applications, including augmented acoustic reality and algorithmic composition.

1. Edwards M. Algorithmic composition: computational thinking in music. Communications of the ACM, 2011, vol. 54, no. 7, pp. 58–67. doi: 10.1145/1965724.1965742

2. Kortuem G., Kawsar F., Sundramoorthy V., Fitton D. Smart objects as building blocks for the internet of  things. IEEE Internet Computing, 2010, vol. 14, no. 1, pp. 44–51. doi: 10.1109/MIC.2009.143

3. Goldshtein B.S., Koucheryavy A. Post-NGN Era Communication Networks. St. Petersburg, BKhV-Peterburg Publ., 2014, 160 p. (In Russian)

4. Berners-Lee T., Hendler J., Lassila O. The semantic web. Scientific American, 2001, vol. 284, no. 5, pp. 34–43. doi: 10.1038/scientificamerican0501-34

5. Dadzie A.-S., Rowe M., Petrelli D. Hide the stack: toward usable linked data. Lecture Notes in Computer Science, 2011, vol. 6643, pp. 93–107. doi: 10.1007/978-3-642-21034-1_7

6. Colton S., Wiggins G.A. Computational creativity: the final frontier? Frontiers in Artificial Intelligence and Applications, 2012, vol. 242, pp. 21–26. doi: 10.3233/978-1-61499-098-7-21

7. McDermott J. Functional representations of music. Proc. 3rd Int. Conf. on Computational Creativity. Dublin, Ireland, 2012. P. 224.

8. Draves S. The electric sheep screen-saver: a case study in aesthetic evolution. Lecture Notes in Computer Science, 2005, vol. 3449, pp. 458–467.

9. Cope D. Computer Models of Musical Creativity. Cambridge, MIT Press, 2005, 456 p.

10. Jones D., Gregson P. The listening machine: generating complex musical structure from social network communications. Proc. 50th Anniversary Convention of the AISB. London, 2014, 6 p.

11. Hermann T., Nehls A.V., Eitel F., Barri T., Gammel M. Tweetscapes – real-time sonification of twitter data streams for radio broadcasting. Proc. 18th Int. Conf. on Auditory Display. Atlanta, USA, 2012, pp. 113–120.

12. Vercoe B. Csound: A Manual for the Audio-Processing System. MIT Media Lab, 1995.

13. Boulanger R. The Csound Book: Perspectives in Software Synthesis, Sound Design, Signal Processing, and Programming. Cambridge, MIT Press, 2000, 782 p.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License