Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing

Abstract In algorithmic music composition, a simple technique involves selecting notes sequentially according to a transition table that specifies the probability of the next note as a function of the previous context. An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT. CONCERT is trained on a set of pieces with the aim of extracting stylistic regularities. CONCERT can then be used to compose new pieces. A central ingredient of CONCERT is the incorporation of psychologically grounded representations of pitch, duration and harmonic structure. CONCERT was tested on sets of examples artificially generated according to simple rules and was shown to learn the underlying structure, even where other approaches failed. In larger experiments, CONCERT was trained on sets of J. S. Bach pieces and traditional European folk melodies and was then allowed to compose novel melodies. Although the compositions are occasionally pleasant, and are...

[1]  Mark B. Ring.  Learning Sequential Tasks by Incrementally Adding Higher Orders , 1992, NIPS.

[2]  D. J. Burr,et al.  Hierarchical recurrent networks for learning musical structure , 1993, Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop.

[3]  Jürgen Schmidhuber,et al.  Continuous history compression , 1993 .

[4]  Mark Dolson.  Machine tongues XII : Neural networks , 1989 .

[5]  Garrison W. Cottrell,et al.  Phase-Space Learning for Recurrent Networks , 1993 .

[6]  Robert O. Gjerdingen.  Learning syntactically significant temporal patterns of chords: A masking field embedded in an ART 3 architecture , 1992, Neural Networks.

[7]  C. Krumhansl.  Cognitive Foundations of Musical Pitch , 1990 .

[8]  Charles Dodge,et al.  Computer Music, Synthesis, Composition, and Performance , 1986 .

[9]  Bart Kosko,et al.  Neural networks for signal processing , 1992 .

[10]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[11]  James L. McClelland.  On the time relations of mental processes: An examination of systems of processes in cascade. , 1979 .

[12]  R. Shepard.  Geometrical approximations to the structure of musical pitch. , 1982, Psychological review.

[13]  Carol L. Krumhansl,et al.  Cognitive Foundations of Musical Pitch , 1992 .

[14]  Catherine Myers.  Learning with Delayed Reinforcement Through Attention-Driven Buffering , 1991, Int. J. Neural Syst..

[15]  Denis Lorrain,et al.  A Panoply of Stochastic 'Cannons' , 1980 .

[16]  Charles Dodge,et al.  Computer Music: Synthesis, Composition, and Performance , 1997 .

[17]  Michael C. Mozer,et al.  A Focused Backpropagation Algorithm for Temporal Pattern Recognition , 1989, Complex Syst..

[18]  C. Krumhansl,et al.  Tracing the dynamic changes in perceived tonal organization in a spatial representation of musical keys. , 1982 .

[19]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent connectionist networks , 1990 .

[20]  T. Kohonen.  A self-learning musical grammar, or 'associative memory of the second kind' , 1989, International 1989 Joint Conference on Neural Networks.

[21]  Peter M. Todd,et al.  A Connectionist Approach To Algorithmic Composition , 1989 .

[22]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[23]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[24]  C. Krumhansl,et al.  Perceived harmonic structure of chords in three related musical keys. , 1982, Journal of experimental psychology. Human perception and performance.

[25]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[26]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[27]  Yoshua Bengio,et al.  The problem of learning long-term dependencies in recurrent networks , 1993, IEEE International Conference on Neural Networks.

[28]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[29]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[30]  Mozer,et al.  RAMBOT (Restructuring Associative Memory Based on Training): a connectionist expert system that learns by example. Technical report, October 1985-April 1986 , 1986 .

[31]  John S. Bridle,et al.  Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters , 1989, NIPS.

[32]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[33]  Geoffrey E. Hinton,et al.  Learning distributed representations of concepts. , 1989 .

[34]  M. R. Jones,et al.  Dynamic attending and responses to time. , 1989, Psychological review.

[35]  Michael C. Mozer,et al.  A Connectionist Symbol Manipulator that Discovers the Structure of Context-Free Languages , 1992, NIPS.

[36]  Jamshed J. Bharucha,et al.  MUSACT: a connectionist model of musical harmony , 1992 .

[37]  Jürgen Schmidhuber,et al.  Learning Unambiguous Reduced Sequence Descriptions , 1991, NIPS.

[38]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[39]  Douglas H. Keefe,et al.  The Representation of Pitch in a Neural Net Model of Chord Classification , 1989 .

[40]  C. Roads,et al.  Grammars as Representations for Music , 1979 .

[41]  R. Jackendoff,et al.  A Generative Theory of Tonal Music , 1985 .

[42]  P. Fraisse.  6 – Rhythm and Tempo , 1982 .

[43]  H. C. Longuet-Higgins,et al.  Perception of melodies , 1976, Nature.

[44]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[45]  Garrison W. Cottrell,et al.  Please Scroll down for Article Connection Science Learning Simple Arithmetic Procedures , 2022 .

[46]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[47]  H. C. Losguet-Higgins.  The Perception of Music , 1978 .

[48]  Teuvo Kohonen,et al.  A nonheuristic automatic composing method , 1991 .

[49]  Peter M. Todd,et al.  Modeling the Perception of Tonal Structure with Neural Nets , 1989 .

[50]  Hugh Christopher Longuet-Higgins,et al.  Review Lecture The perception of music , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[51]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[52]  Michael C. Mozer,et al.  Induction of Multiscale Temporal Structure , 1991, NIPS.

[53]  Kevin I. Jones,et al.  Compositional Applications of Stochastic Processes , 1981 .

[54]  Lawrence D. Jackel,et al.  Large Automatic Learning, Rule Extraction, and Generalization , 1987, Complex Syst..

[55]  R. Shepard,et al.  Toward a universal law of generalization for psychological science. , 1987, Science.