Citation
Alexandre Donze, Libkind Sophie, Sanjit Seshia, David Wessel. "Control Improvisation with Application to Music". Technical report, UC Berkeley, P068797, November, 2013.

Abstract
We introduce the concept of control improvisation, the process of generating a random sequence of control events guided by a reference sequence and satisfying a given specification. We propose a formal definition of the control improvisation problem and an empirical solution applied to the domain of music. 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

• Control_Impro_TR.pdf · application/octetstream · 854 kbytes
• http://www.src.org/library/publication/p068797/. (SRC Website.)

• HTML

  Alexandre Donze, Libkind Sophie, Sanjit Seshia, David
  Wessel. <a
  href="http://www.terraswarm.org/pubs/189.html"
  ><i>Control Improvisation with Application to
  Music</i></a>, Technical report,  UC Berkeley,
  P068797, November, 2013.

• Plain text

  Alexandre Donze, Libkind Sophie, Sanjit Seshia, David
  Wessel. "Control Improvisation with Application to
  Music". Technical report,  UC Berkeley, P068797,
  November, 2013.

• BibTeX

  @techreport{DonzeSophieSeshiaWessel13_ControlImprovisationWithApplicationToMusic,
      author = {Alexandre Donze and Libkind Sophie and Sanjit
                Seshia and David Wessel},
      title = {Control Improvisation with Application to Music},
      institution = {UC Berkeley},
      number = {P068797},
      month = {November},
      year = {2013},
      abstract = { We introduce the concept of control
                improvisation, the process of generating a random
                sequence of control events guided by a reference
                sequence and satisfying a given specification. We
                propose a formal definition of the control
                improvisation problem and an empirical solution
                applied to the domain of music. 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/189.html}
  }
  

Posted by Alexandre Donze on 11 Nov 2013.
Groups: tools