This workshop explored machine learning approaches to 3 topics: (1) finding structure in music (analysis, continuation, and comple(cid:173) tion of an unfinished piece), (2) modeling perception of time (ex(cid:173) 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(cid:173) 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 to the question "When next?" . In other words, so far we have considered patterns in time. They assume prior iden(cid:173) tification and subsequent processing of events. Bob Port, coming from the speech community, considered patterns of time, discussing timing in linguistic polyrhythms (e.g., hot cup of tea). He also drew parallels between timing in Japanese language and timing in music, supporting the hypothesis that perceptional rhythms entrain attentional rhythms. As a mechanism for entrainment, Devin McAuley presented adaptive oscillators: the oscillators adapt their frequencies such that their "firing" coincides with the beat of the music (McAuley, 1994).
As the beat can be viewed as entrainment of an individual oscillator, the meter can be viewed as entrainment of multiple oscillators. Ed Large described human perception of metrical structure in analogy to two pendulum clocks that synchronize their motions by hanging on the same wall. An advantage of these entrainment
1 This fugue is available via anonymous ftp from ftp. santafe. edu as data set F. dat of
the Santa Fe Time Series Analysis and Prediction Competition.