Specification Mining For Machine Improvisation With Formal Specifications
Rafael Valle, Alexandre Donze, Daniel J. Fremont, Ilge Akkaya, Sanjit Seshia, Adrian Freed, David Wessel

Citation
Rafael Valle, Alexandre Donze, Daniel J. Fremont, Ilge Akkaya, Sanjit Seshia, Adrian Freed, David Wessel. "Specification Mining For Machine Improvisation With Formal Specifications". Talk or presentation, October, 2015.

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 learn from symbolic musical data specifications based on 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 musical form. We present a specification mining strategy based on finite state automata and Markov chains, 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 supervised and unsupervised improvisations.

Electronic downloads


Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.
Citation formats  
  • HTML
    Rafael Valle, Alexandre Donze, Daniel J. Fremont, Ilge
    Akkaya, Sanjit Seshia, Adrian Freed, David Wessel. <a
    href="http://www.terraswarm.org/pubs/678.html"
    ><i>Specification Mining For Machine Improvisation
    With Formal Specifications</i></a>, Talk or
    presentation,  October, 2015.
  • Plain text
    Rafael Valle, Alexandre Donze, Daniel J. Fremont, Ilge
    Akkaya, Sanjit Seshia, Adrian Freed, David Wessel.
    "Specification Mining For Machine Improvisation With
    Formal Specifications". Talk or presentation,  October,
    2015.
  • BibTeX
    @presentation{ValleDonzeFremontAkkayaSeshiaFreedWessel15_SpecificationMiningForMachineImprovisationWithFormal,
        author = {Rafael Valle and Alexandre Donze and Daniel J.
                  Fremont and Ilge Akkaya and Sanjit Seshia and
                  Adrian Freed and David Wessel},
        title = {Specification Mining For Machine Improvisation
                  With Formal Specifications},
        month = {October},
        year = {2015},
        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 learn from symbolic musical
                  data specifications based on 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 musical form. We present a
                  specification mining strategy based on finite
                  state automata and Markov chains, 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
                  supervised and unsupervised improvisations.},
        URL = {http://terraswarm.org/pubs/678.html}
    }
    

Posted by Rafael Valle on 15 Oct 2015.
Groups: tools

Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.