Abstract
We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive computer environment. In the second framework, the stylistic interaction is delegated to machine intelligence and therefore, knowledge propagation and decision are taken care of by the computer alone. The first framework involves a hybrid architecture using two popular composition/performance environments, Max and OpenMusic, that are put to work and communicate together, each one handling the process at a different time/memory scale. The second framework shares the same representational schemes with the first but uses an Active Learning architecture based on collaborative, competitive and memory-based learning to handle stylistic interactions. Both systems are capable of processing real-time audio/video as well as MIDI. After discussing the general cognitive background of improvisation practices, the statistical modelling tools and the concurrent agent architecture are presented. Then, an Active Learning scheme is described and considered in terms of using different improvisation regimes for improvisation planning. Finally, we provide more details about the different system implementations and describe several performances with the system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
It should be noted that the use of the term Learning in AL refers to the ability to adaptively select the best repertoire for improvisation (we refer to this as second mode), which is different from the learning aspect involved in construction of the musical dynamic memory that is central to the first mode of operation. The term learning refers here to learning of the criteria or the costs involved in selection of repertoire that would be appropriate for interaction, and it should be distinguished from the learning involved in forming the stylistic memory. The reason for using this term in AL is for its common use in the artificial intelligence literature.
- 2.
References
Allauzen C, Crochemore M, Raffinot M (1999) Factor oracle: a new structure for pattern matching. In: Proceedings of conference on current trends in theory and practice of informatics, Springer, London, pp 295–310
Assayag G, Bloch G, Chemillier M (2006) Improvisation et réinjection stylistique. In: Yann O (ed) Actes des recontres musicales pluridisciplinaires. Grame, Lyon
Assayag G, Dubnov S (2004) Using factor oracles for machine improvisation. Soft Comput 8–9:604–610
Assayag G, Dubnov S, Delerue O (1999) Guessing the composer’s mind: applying universal prediction to musical style. In: ICMC: international computer music conference, MIT Press, Beijing, China, October 1999
Biles JA (2003) Genjam in perspective: a tentative taxonomy for genetic algorithm music and art systems. Leonardo 36(1):43–45
Chalot X, Dannenberg R, Bloch G (1986) A workstation in live performance: composed improvisation. In: International computer music conference (ICMC). MIT Press, The Hague, pp 537–540
Cohn DA, Atlas L, Ladner RE (1994) Improving generalization with active learning. Mach Learn 15(2):201–221
Conklin D (2003) Music generation from statistical models. In: Gervas P, Colton S (eds) Proceedings of symposium on AI and creativity in the arts and sciences. Aberystwyth, Wales, pp 30–35
Cont A, Dubnov S, Assayag G (2007) Anticipatory model of musical style imitation using collaborative and competitive reinforcement learning. In: Butz MV, Sigaud O, Pezzulo G, Baldassarre G (eds) Anticipatory behavior in adaptive learning systems, vol. 4520 of LNAI. Springer, Berlin, pp 285–306
Cont A, Dubnov S, Assayag G (2007) Guidage: a fast audio query guided assemblage. In: Proceedings of international computer music conference (ICMC), MIT Press, Copenhagen, September 2007
de Cheveign A, Kawahara H (2002) YIN, a fundamental frequency estimator for speech and music. J Acoust Soc Am 111:1917–1930
Dubnov S, Assayag G, Cont A (2007) Audio oracle: a new algorithm for fast learning of audio structures. In: Hallam B, Floreano D, Hallam J, Hayes G, Meyer J-A (eds) Proceedings of international computer music conference (ICMC), Copenhagen, September 2007
Dubnov S, Assayag G, El-Yaniv R (1998) Universal classification applied to musical sequences. In: Proceedings of ICMC, Grame Michigan, pp 322–340
Dubnov S, Assayag G, Lartillot O, Bejerano G (2003) Using machine-learning methods for musical style modeling. IEEE Comput Soc 36(10):73–80
Held R, Hein A (1963) Movement-produced stimulation in the development of visually guided behavior. J Comp Physiol Psych 56:872–876
Huron D Sweet anticipation: music and the psychology of expectation. MIT Press, Cambridge, MA
Lewis G (2000) Too many notes: computers, complexity and culture in voyager. Leonardo Music J 10:33–39
Moore A, Atkeson C (1993) Prioritized sweeping: reinforcement learning with less data and less real time. Mach Learn 13:103–130
Noë A (2004) Action in perception. MIT Press, Boston, MA
Pachet F (2006) Interactions réflexives. In: Yann O (ed) Actes des recontres musicales pluridisciplinaires. Grame, Lyon
Ron D, Singer Y, Tishby N (1996) The power of amnesia: learning probabilistic automata with variable memory length. Mach Learn 25(2–3):117–149
Simon HA (1969) The science of the artificial. MIT Press, Boston, MA
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge, MA
Uchibe E, Doya K (2004) Competitive-cooperative-concurrent reinforcement learning with importance sampling. In: Schaal S, Ijspeert AJ, Billard A, Vijayakumar S, Hallam J, Meyer JA (eds) Proceedings of international conference on simulation of adaptive behavior: from animals and animats. Los Angeles, CA, pp 287–296
Wessel D (2006) An enactive approach to computer music performance. In: Yann O (ed) Actes des recontres musicales pluridisciplinaires. Grame, Lyon
Wessel D, Wright M (2001) Problems and prospects for prospects for intimate musical control of computers. In: New interfaces for musical expressions (NIME). International Computer Music Association, San Francisco, CA
Wright M (2005) Open sound control: an enabling technology for musical networking. Organis Sound 10(3):193–200
Zicarelli D (1987) M Jam factory. Comput Music J 11(4):13–29
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Assayag, G., Bloch, G., Cont, A., Dubnov, S. (2010). Interaction with Machine Improvisation. In: Argamon, S., Burns, K., Dubnov, S. (eds) The Structure of Style. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12337-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-12337-5_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12336-8
Online ISBN: 978-3-642-12337-5
eBook Packages: Computer ScienceComputer Science (R0)