Tonal Music as a Componential Code: Learning Temporal Relationships between and within Pitch and Timing Components

This study explores the extent to which a network that learns the temporal relationships within and between the component features of Western tonal music can account for music theoretic and psychological phenomena such as the tonal hierarchy and rhythmic expectancies. Predicted and generated sequences were recorded as the representation of a 153-note waltz melody was learnt by a predictive, recurrent network. The network learned transitions and relations between and within pitch and timing components: accent and duration values interacted in the development of rhythmic and metric structures and, with training, the network developed chordal expectancies in response to the activation of individual tones. Analysis of the hidden unit representation revealed that musical sequences are represented as transitions between states in hidden unit space.

[1]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[2]  J. Bharucha.  Music Cognition and Perceptual Facilitation: A Connectionist Framework , 1987 .

[3]  Samir I. Sayegh,et al.  Fingering for string instruments with the optimum path paradigm , 1989 .

[4]  Catherine J. Stevens,et al.  Judgments of complexity and pleasingness in music: The effect of structure, Repetition, and training , 1991 .

[5]  Paul Smolensky,et al.  Virtual Memories and Massive Generalization in Connectionist Combinatorial Learning ; CU-CS-431-89 , 1989 .

[6]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .

[7]  R. Shepard,et al.  Quantification of the hierarchy of tonal functions within a diatonic context. , 1979, Journal of experimental psychology. Human perception and performance.

[8]  James L. McClelland,et al.  Generalization with Componential Attractors: Word and Nonword Reading in an Attractor Network , 1993 .

[9]  J. Bharucha,et al.  Reaction time and musical expectancy: priming of chords. , 1986, Journal of experimental psychology. Human perception and performance.

[10]  Roger A. Kendall,et al.  The effect of melodic and temporal contour on recognition memory for pitch change , 1987, Perception & psychophysics.

[11]  David Rosenthal,et al.  Emulation of human rhythm perception , 1992 .

[12]  Wolfram Menzel,et al.  HARMONET: A Neural Net for Harmonizing Chorales in the Style of J. S. Bach , 1991, NIPS.

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

[14]  Mari Riess Jones.  Attending to musical events. , 1992 .

[15]  Janet Wiles,et al.  Operators and Curried Functions: Training and Analysis of Simple Recurrent Networks , 1991, NIPS.

[16]  Jamshed J. Bharucha,et al.  Tonality and learnability. , 1992 .

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

[18]  Janet Wiles,et al.  Exponential generalizations from a polynomial number of examples in a combinatorial domain , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).