Citation
Rafael Valle, Alexandre Donze, Ilge Akkaya, Sophie Libkind, Sanjit Seshia, David Wessel. "Machine Improvisation with Formal Specifications". ICMCSMC14, 2014.

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.

Electronic downloads

• https://www.src.org/library/publication/p070207/. (Link to paper on SRC website.)
• http://quod.lib.umich.edu/i/icmc/bbp2372.2014.196/1
• http://escholarship.org/uc/item/2cb6x3fp. (link to eScholarship site)

• HTML

  Rafael Valle, Alexandre Donze, Ilge Akkaya, Sophie Libkind,
  Sanjit Seshia, David Wessel. <a
  href="http://www.terraswarm.org/pubs/311.html"
  >Machine Improvisation with Formal
  Specifications</a>, <i>ICMCSMC14</i>, 
  2014.

• Plain text

  Rafael Valle, Alexandre Donze, Ilge Akkaya, Sophie Libkind,
  Sanjit Seshia, David Wessel. "Machine Improvisation
  with Formal Specifications".
  <i>ICMCSMC14</i>,  2014.

• BibTeX

  @article{ValleDonzeAkkayaLibkindSeshiaWessel14_MachineImprovisationWithFormalSpecifications,
      author = {Rafael Valle and Alexandre Donze and Ilge Akkaya
                and Sophie Libkind and Sanjit Seshia and David
                Wessel},
      title = {Machine Improvisation with Formal Specifications},
      journal = {ICMCSMC14},
      year = {2014},
      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. },
      URL = {http://terraswarm.org/pubs/311.html}
  }
  

Posted by Alexandre Donze on 12 May 2014.
Groups: tools