Connectionism for music and audition

This workshop explored machine learning approaches to 3 topics: (1) finding structure in music (analysis, continuation, and comple-tion of an unfinished piece), (2) modeling perception of time (ex-traction of musical meter, explanation of human data on timing), and (3) interpolation in timbre space. In recent years, NIPS has heard neural networks generate tunes and harmonize chorales. With a large amount of music becoming available in computer readable form, real data can be used to train connectionist models. At the beginning of this workshop, Andreas Weigend focused on architectures to capture structure on multiple time scales. J. S. Bach's last (unfinished) fugue from Die Kunst der Fuge served as an example (Dirst & Weigend, 1994).1 The prediction approach to continuation and completion, as well as to modeling expectations, can be charac-terized by the question "What's next?". Moving to time as the primary medium of musical communication, the inquiry in music perception and cognition shifted t