The Taub Faculty of Computer Science Events and Talks

Learning to generate music is an ongoing AI challenge. A more difficult challenge is the generation of musical pieces that match human-specific preferences. In this work we focus on personalized, symbol-based, monophonic generation of harmony-constrained jazz improvisations. To tackle this objective, we introduce a pipeline consisting of the following steps: supervised learning using a corpus of solos, high-resolution user preference metric learning, and optimized generation using planning (beam search). Our corpus consists of hundreds of original jazz solos performed by saxophone giants such as Charlie Parker. We present an extensive empirical study in which we apply this pipeline to extract individual models as implicitly defined by several human listeners. Our approach enables an objective examination of subjective personalized models whose performance is quantifiable. The results indicate that it is possible to model and optimize personalized jazz preferences.