Computer Music Modeling and Retrieval

CMMR, Pisa, Italy 26-28 September 2005

This was a rather small conference, with only about 40 participants, organised at the CNR in lovely Pisa. The topics presented were varied, but here, as in most other computer music conferences these days, there were a high percentage of music information retrieval presentations. I was there to present a short paper on building low-cost music controllers from hacked gamepads and homemade sensors, something I worked on while at McGill in the spring. A summary of things I found interesting:

  • Mark Havryliv and Terumi Narushima, Wollongong University, Australia, presented Metris, a Tetris-like game for music. Unfortunately, I arrived right after their presentation, but the concept seems very interesting.
  • Laurent Pottier, GMEM, presented a microsound system implemented in Max/MSP, and different ways of controlling it. I am looking forward to the release of the objects.
  • Leonello Tarabella, Pisa, played with his "air piano" system using video analysis. It worked very well considering the obvious problems with resolution and speed of video cameras.
  • Carlos Guedes, NYU and Porto, presented a dance-piece using the m-objects that he presented ICMC a couple of weeks ago. He has been focusing on rhythmic aspects of dance movements and implementations in music. Very nice!
  • Philippe Guillemain, CNRS Marseille, presented work on transitions in reed instruments. This is perceptually very relevant, and it is strange that it has not received greater attention earlier.
  • Giordano Cabral, Paris 6, presented something Francois Pachet covered very quickly at the S2S^2 summer school, and this time I actually understood some more. It is about using the Extractor Discovery System (EDS) for recognition. It is using a genetic algorithm to automatically build extraction algorithms from a set of basic mathematics and signal processing operators. For the user, this makes it possible to ask the system to develop different types of equations, and make it find the best ones. Seems very interesting, and apparently it works.
  • Markus Schedl, Johannes Kepler University, Linz , presented a web-mining paper, where they had been building artist ranking tables withing various musical styles based on querying for artist-pairs. The novel thing was how they had made a penalizing system, to avoid over-ranking of artists with names similar to common words (kiss, prince, madonna). I find it fascinating that such systems, which are completely ignorant of any music theory, manage to come up with results which seems to be very "correct" in terms of human classification.
  • Rodrigo Segnini and Craig Sapp, CCRMA and CCARH, Stanford, presented the ideas of making Scoregrams from notation. This is basically a way of generating "spectrograms" of a symbolic signal. The point is to be able to quickly visualize what is going on at different levels in the music. They have made them so that the window size they are looking at is decreasing from bottom to top. This gives a very detailed image at the bottom and only one value on top.
  • Snorre Farner, NTNU, presented work on "naturalness" in clarinet play, and jump-started a discussion on the concept of naturalness, expressivness etc. Definitely a burning topic these days!
  • Christophe Rhodes, Goldsmiths, London, had made a system for writing lute tablature. Kind of a niche thing, but it looked very neat!
  • Mark Marshall, McGill, presented results from some preliminary tests on the usability of various sensors for musical applications. I think this is a very important topic, and I hope he continues to look into this. At the moment he has been focusing on pitch/melody related issues, but this should be extended to also cover rhythmical and timbral elements.
  • Kristoffer Jensen, Aalborg, showed some very interesting examples of the boundaries between noice and tonal sound.
  • Cynthia Grund, Odense, called for a panel on interdisciplinarity issues. Coming from music philosophy, she called for more coopeartion between the technologies and the "traditional" humanities. Many coming from a technical side would benefit from looking at recent issues in the humanities, and vice versa. What is quite clear is that most people working in the humanities have not realized the exponential growth in the Music Information Retrieval in the last years, driven by strong commercial and application-based (internet queries) interests.

Published by


Alexander Refsum Jensenius is a music researcher and research musician living in Oslo, Norway.