M.Sc Thesis

M.Sc StudentBhonker Nadav
SubjectNeural Models for Personalized Jazz Improvisations
DepartmentDepartment of Computer Science
Supervisor PROF. Ran El-Yaniv
Full Thesis textFull thesis text - English Version


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 (a language model), 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, Stan Getz, Sonny Stitt and Dexter Gordon. 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. In addition, our subjective impression is that the resulting computer-generated solos are often musically appealing. We also perform a plagiarism analysis to ensure that the generated solos are genuine rather than a concatenation of phrases previously seen in the corpus. Numerous MP3 demonstrations of solos generated by our system are provided in the supplementary material.