University of Cambridge > Talks.cam > NLIP Seminar Series > Parsing Jazz: Harmonic Analysis of Music Using Combinatory Categorial Grammar

Parsing Jazz: Harmonic Analysis of Music Using Combinatory Categorial Grammar

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar.

In Western tonal music, an important part of a listener’s understanding of a piece of music is an unconscious analysis of the harmonic progression underlying it. Harmonic progressions in tonal music have been described as having a hierarchical structure, similar to that found in the syntax and semantics of natural language. This work demonstrates the use of grammar-based parsing, with standard machine-learning techniques from NLP , for automatic analysis of the structure of jazz chord sequences, according to a theory in the tradition of functional harmonic analysis.

This talk will introduce the theory of harmonic structure underlying the work and a grammar formalism, based on CCG , suitable for processing the syntax of tonal harmony. It will then address the practical problem of automatic harmonic analysis by adapting some statistical parsing techniques from natural language processing. The results of parsing experiments indicate that the constraints of a grammar help in recovering harmonic analyses, when compared with a Markovian approach.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity