|
Modeling Jazz Virtuosity| old_uid | 8086 |
|---|
| title | Modeling Jazz Virtuosity |
|---|
| start_date | 2010/02/03 |
|---|
| schedule | 16h-17h |
|---|
| online | no |
|---|
| summary | Virtuosity can be observed in many domains of human performance, from Jazz improvisation to fast mental computation. This fascinating dimension of human behavior is, however, poorly studied outside of the field of art history.
In this talk I focus on the particular problem of generating virtuoso Bebop melodies. The problem of modeling Jazz improvisation has received a lot of attention recently, thanks to progresses in machine learning, statistical modeling, and to the increase in computation power of machines. The Continuator (Pachet, 2003) was the first real time interactive systems to allow users to create musical dialogs using style learning techniques. The Continuator is based on a modeling of musical sequences using Markov chains, a technique that was shown to be well adapted to capture stylistic musical patterns, notably in the pitch domain. The Continuator had great success in free-form improvisational settings, in which the users explore freely musical language created on-the-fly, without additional musical constraints, and was used with Jazz musicians as well as with children (Addessi & Pachet, 2005). However, the Continuator, like most systems using Markovian approaches, is difficult, if not impossible to control. This limitation is intrinsic to the greedy, left-to-right nature of Markovian music generation algorithms. Consequently, it was so far difficult to use these systems in highly constrained musical contexts such as Bebop.
I propose here a computational model of virtuosity based on a novel, combinatorial view of Markov sequence generation. This model solves the "control" problem inherent to Markov chain geeneration, and also provides a very fine degree of control to the user. I illustrate this work with a controlable Bebop improvisation generator. Bebop was chosen as it is a particularly “constrained” style, notably harmonically. I will show how this technique can generate improvisations that satisfy three types of constraints: 1) harmonic constraints derived from the rules of Bebop, 2) “Side-slips” as a way to extend the boundaries of Markovian generation by producing locally dissonant but semantically equivalent musical material that smoothly comes back to the authorized tonalities, and 3) non-Markovian constraints deduced from the user’s gestures. I will try to convince the audience that these generated phrases 1) are of the same nature than what real virtuoso are able to generate and that 2) the ability to control these phrases is an highly enjoyable process.
Bio: Francois Pachet got a Ph.D in Artificial Intelligence from the University of Paris 6. He is now senior researcher at Sony Computer Science Laboratories in Paris, where he conducts research on new forms of musical experiences. |
|---|
| responsibles | Bishop |
|---|
| |
|