Recurrent neural networks for music computation

INFORMS Journal on Computing

Volumn 18, Issue 3, 2006, Pages 321-338

  Franklin, Judy A ^a  

^a SMITH COLLEGE   (United States)

Author keywords

Computer music; LSTM; Music representation; Recurrent neural networks

Indexed keywords

EID: 33748574514     PISSN: 10919856     EISSN: 15265528     Source Type: Journal    
DOI: 10.1287/ijoc.1050.0131     Document Type: Article

References (31)

1. Allen, P., R. Dannenberg. 1990. Tracking musical beats in real time. Internat. Comput. Music Conf., International Computer Music Association, San Francisco, CA, 140-143.
2. Berg, S. 1990. Jazz Improvisation: The Goal-Note Method, 2nd ed. Kendor Music, Inc., Delevan, NY.
3. Campolucci, P. 1998. A circuit theory approach to recurrent neural network architectures and learning methods. Ph.D. thesis, Dipartimento di Ingegneria Elettrica, Universitá Degli Studi di Bologna, Bologna, Italy.
4. Dannenberg, R., B. Thom, D. Watson. 1997. A machine learning approach to musical style recognition. Proc. Internat. Comput. Music Conf. ICMA, San Francisco, CA, 344-347.
5. Desain, P., H. Honing, K. de Rijk. 1989. A connectionist quantizer. Proc. 1989 Internat. Comput. Music Conf. ICMA, San Francisco, CA, 80-85.
6. Eck, D., J. Schmidhuber. 2002. Learning the long-term structure of the blues. Proc. 2002 Internat. Conf. Artificial Neural Networks (ICANN), 284-289.
7. Franklin, J. A. 2000. Multi-phase learning for jazz improvisation and interaction. Proc. Eighth Biennial Connecticut College Sympos. Arts and Tech. Connecticut College, New London, CT, 51-60.
8. Franklin, J. A. 2002. Learning and improvisation. T. G. Dietterich, S. Becker, Z. Ghahramani, eds. Neural Information Processing Systems 14. MIT Press, Cambridge, MA, 1377-1384.
9. Franklin, J. A. 2004a. Recurrent neural networks and pitch representations for music tasks. Proc. 2004 Florida AI Research Sympos. (FLAIRS04) Special Track on AI and Music. AAAI Press, Cambridge, MA, 33-37.
10. Franklin, J. A. 2004b. Predicting reinforcement of pitch sequences via LSTM and TD. Proc. 2004 Internat. Comput. Music Conf. ICMA, San Francisco, CA, 130-136.
11. Gers, F. A., J. Schmidhuber, F. Cummins. 2000. Learning to forget: Continual prediction with LSTM. Neural Comput. 12(10) 2451-2471.
12. Griffith, N., P. Todd. 1999. Musical Networks: Parallel Distributed Perception and Performance. MIT Press, Cambridge, MA.
13. Hochreiter, S., Y. Bengio, P. Frasconi, J. Schmidhuber. 2001. Gradient flow in recurrent nets: The difficulty of learning long-term dependencies. A Field Guide to Dynamical Recurrent Networks. IEEE Press, New York.
14. Hochreiter, S., J. Schmidhuber. 1997. Long short-term memory. Neural Comput. 9(8) 1735-1780.
15. Jordan, M. 1986. Attractor dynamics and parallelism in a connectionist sequential machine. Proc. Eighth Annual Conf. Cognitive Sci. Soc., Amherst, MA, 531-546.
16. Kolen, J. F., S. C. Kremer. 2001. A Field Guide to Dynamical Recurrent Networks. IEEE Press, New York.
17. Laden, B., D. H. Keefe. 1991. The representation of pitch in a neural net model of chord classification. P. M. Todd, E. D. Loy, eds. Music and Connectionism. MIT Press, Cambridge, MA.
18. Large, E. W., J. F. Kolen. 1994. Resonance and the perception of musical meter. Connection Sci. 6(2 & 3) 177-208.
19. Mandic, D. P., J. A. Chambers. 2001. Recurrent Neural Networks for Prediction. Wiley, West Sussex, UK.
20. Messick, P. 1988. Maximum MIDI. Manning Publications, Greenwich, CT.
21. Mozer, M. C. 1994. Neural network music composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Connection Sci. 6 247-280.
22. PG Music. Band-in-a-Box. http://www.pgmusic.com/bandbox.htm.
23. Rumelhart, D., G. Hinton, R. Williams. 1986. Learning internal representations by error propagation. D. E. Rumelhart, J. L. McClelland, eds. Parallel Distributed Processing 1. MIT Press, Cambridge, MA, 318-362.
24. Sabatella, M. 1996. A Whole Approach to Jazz Improvisation. ADG Productions, Lawndale, CA.
25. Shepard, R. N. 1987. Toward a universal law of generalization for psychological science. Science 237 1317-1323.
26. Steedman, M. 1994. The well-tempered computer. Philos. Trans. Roy. Soc. Ser. A 149 115-131.
27. Thompson, T. 2003. Keykit programming language and graphical environment for MIDI, http://nosuch.com/tjt/.
28. Todd, P. M. 1991. A connectionist approach to algorithmic composition. P. M. Todd, E. D. Loy, eds. Music and Connectionism. MIT Press, Cambridge, MA.
29. Todd, P. M., E. D. Loy. 1991. Music and Connectionism. MIT Press, Cambridge, MA.
30. Williams, R. J., J. Peng. 1990. An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Comput. 2(4) 490-501.
31. Williams, R. J., D. Zipser. 1988. A learning algorithm for continually running fully recurrent networks. Technical Report ICS-8805, Institute for Cognitive Science, University of California, San Diego, CA.