Specification Mining for Machine Improvisation with Formal Specifications

Rafael Valle, Alexandre Donzé, Daniel J. Fremont, Ilge Akkaya, Sanjit A. Seshia, Adrian Freed, and David Wessel. Specification Mining for Machine Improvisation with Formal Specifications. ACM Computers in Entertainment, 14(3), ACM, 2016.

Download

[pdf] 

Abstract

We address the problem of mining musical specifications from a training set of songs and using these specifications in a machine improvisation system capable of generating improvisations imitating a given style of music. Our inspiration comes from Control Improvisation, which combines learning and synthesis from formal specifications. We mine specifications from symbolic musical data with musical and general usage patterns. We use the mined specifications to ensure that an improvised musical sequence satisfies desirable properties given a harmonic context and phrase structure. We present a specification mining strategy based on pattern graphs and apply it to the problem of supervising the improvisation of blues songs. We present an analysis of the mined specifications and compare the results of improvisations generated with and without specifications.

BibTeX

@ARTICLE{valle-msm16, 
  author    = {Rafael Valle and Alexandre Donz{\'{e}} and Daniel J. Fremont and Ilge Akkaya and Sanjit A. Seshia and Adrian Freed and David Wessel},
  title     = {Specification Mining for Machine Improvisation with Formal Specifications},
  journal   = {ACM Computers in Entertainment},
  volume = {14},
  number = {3},
  year = {2016},
  issue_date = {Fall 2016},
  issue_description = {Special Issue on Musical Metacreation, Part II},
  publisher = {ACM},
    Abstract = {We address the problem of mining musical specifications from a training set of songs and using these specifications in a 
machine improvisation system capable of generating improvisations imitating a given style of music. Our inspiration comes 
from Control Improvisation, which combines learning and synthesis from formal specifications. We mine specifications 
from symbolic musical data with musical and general usage patterns. We use the mined specifications to ensure that an 
improvised musical sequence satisfies desirable properties given a harmonic context and phrase structure. We present a 
specification mining strategy based on pattern graphs and apply it to the problem of supervising the improvisation of blues 
songs. We present an analysis of the mined specifications and compare the results of improvisations generated with and 
without specifications.},
}