Machine Improvisation with Formal Specifications

Alexandre Donzé, Rafael Valle, Ilge Akkaya, Sophie Libkind, Sanjit A. Seshia, and David Wessel. Machine Improvisation with Formal Specifications. In Proceedings of the 40th International Computer Music Conference (ICMC), pp. 1277–1284, September 2014. Available online at http://hdl.handle.net/2027/spo.bbp2372.2014.196.

Download

[pdf] 

Abstract

We define the problem of machine improvisation of music with formal specifications. In this problem, one seeks to create a random improvisation of a given reference melody that however satisfies a specification encoding constraints that the generated melody must satisfy. More specifically, we consider the scenario of generating a monophonic Jazz melody (solo) on a given song harmonization. The music is encoded symbolically, with the improviser generating a sequence of note symbols comprising pairs of pitches (frequencies) and discrete durations. Our approach can be decomposed roughly into two phases: a generalization phase, that learns from a training sequence (e.g., obtained from a human improviser) an automaton generating similar sequences, and a supervision phase that enforces a specification on the generated sequence, imposing constraints on the music in both the pitch and rhythmic domains. The supervision uses a measure adapted from Normalized Compression Distances (NCD) to estimate the divergence between generated melodies and the training melody and employs strategies to bound this divergence. An empirical evaluation is presented on a sample set of Jazz music.

BibTeX

@InProceedings{donze-icmc14,
  author = 	 {Alexandre Donz{\'{e}} and Rafael Valle and Ilge Akkaya and Sophie Libkind and Sanjit A. Seshia and David Wessel},
  title = 	 {Machine Improvisation with Formal Specifications},
  booktitle = 	 {Proceedings of the 40th International Computer Music Conference (ICMC)},
  OPTcrossref =  {},
  OPTkey = 	 {},
  pages = 	 {1277--1284},
  year = 	 {2014},
  OPTeditor = 	 {},
  OPTvolume = 	 {},
  OPTnumber = 	 {},
  OPTseries = 	 {},
  OPTaddress = 	 {},
  month = 	 {September},
  OPTorganization = {},
  OPTpublisher = {},
  note = 	 {Available online at \url{http://hdl.handle.net/2027/spo.bbp2372.2014.196}.},
  OPTannote = 	 {},
  abstract={We define the problem of machine improvisation of music 
with formal specifications. In this problem, one seeks to 
create a random improvisation of a given reference melody 
that however satisfies a specification encoding constraints 
that the generated melody must satisfy. More specifically, 
we consider the scenario of generating a monophonic Jazz 
melody (solo) on a given song harmonization. The music 
is encoded symbolically, with the improviser generating a 
sequence of note symbols comprising pairs of pitches (frequencies) 
and discrete durations. Our approach can be decomposed 
roughly into two phases: a generalization phase, 
that learns from a training sequence (e.g., obtained from 
a human improviser) an automaton generating similar sequences, 
and a supervision phase that enforces a specification 
on the generated sequence, imposing constraints on 
the music in both the pitch and rhythmic domains. The supervision 
uses a measure adapted from Normalized Compression 
Distances (NCD) to estimate the divergence between 
generated melodies and the training melody and employs 
strategies to bound this divergence. An empirical 
evaluation is presented on a sample set of Jazz music.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun Jun 21, 2015 12:08:13