Index of /~echew/papers/CC2007

 Name                    Last modified      Size  Description
 Parent Directory                             -   
 chuanchew_cc07.pdf      30-Jul-2007 20:16  163K  
 reference.txt           01-Jun-2010 17:07  436   

In this directory are the PDF files for a paper titled

"A Hybrid System for Automatic Generation of Style-Specific Accompaniment"
by Ching-Hua Chuan (chinghuc@usc.edu) and Elaine Chew (echew@usc.edu)

The results were presented by Ching-Hua Chuan at the 
4th International Joint Workshop on Computational Creativity
held at Goldsmiths, University of London, London, UK.  
June 17-19, 2007.

The paper is published in the Proceedings of the 4th IJWCC
Click on reference.txt for the BibTeX reference.

The conference website is at 
http://www.doc.gold.ac.uk/isms/CC07

THE COMPLETE PAPER, text with figures, can be viewed as a PDF document.
Click on chuanchew_cc07.pdf if you wish to view the paper in PDF format.

--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--

"A Hybrid System for Automatic Generation of Style-Specific Accompaniment"
by Ching-Hua Chuan (chinghuc@usc.edu) and Elaine Chew (echew@usc.edu)

ABSTRACT: Creating distinctive harmonizations in an identifiable style
may be one of the most difficult tasks for amateur song writers, a
novel and acceptable melody being relatively easier to produce; and
this difficulty may result in the abandonment of otherwise worthwhile
projects. To model and assist in this creative process, we propose a
hybrid system for generating style-specific accompaniment, which is
capable of creating new harmonizations for melodies, with proper
harmonic resolutions, in a style that is learned from only a few
examples. In the proposed system, a chord tone determination module
first learns, then determines, which notes in a given melody are
likely chord tones. According to these chord tones, triads are
assigned first to the bars with unambiguous solutions, and these
triads serve as checkpoints. The system then constructs possible chord
progressions using neo-Riemannian transforms between checkpoints, and
represents the alternate paths in a tree structure. A Markov chain
with learned probabilities for these neo-Riemanian transforms then
generates the final chord progression. We select four songs by the
British rock band, Radiohead, to evaluate the system. Three songs are
used for training, and an accompaniment is generated for the held out
melody. We present the results of two case studies. We find that the
system generates chords closely related to the original, and the
resulting chord transitions reinforce the phrase structure of the
melody.

Keywords: Automatic Style-Specific Accompaniment, Chord Tone
Determination, Neo-Riemannian Transforms, Markov Chains.