Improving and adapting finite state transducer methods for musical accompaniment

Jonathan P. Forsyth, Rachel M. Bittner, Michael Musick, Juan P. Bello

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

A common area of research within music technology is the automatic generation of musical accompaniment. Of particular interest is the generation of harmonic accompaniment to melody. While there are many approaches to solving this problem, the use of various types of finite state machines is popular. One such finite state machine, the finite state transducer (FST), has been used in a few accompaniment generation systems. Although the FST is widely used in speech recognition, its application in accompaniment generation systems has been relatively unsophisticated. In this paper, we introduce an improved approach to generating harmonic accompaniment to melody based on techniques used in speech recognition. In addition, we describe how we extend this method to the generation of rhythmic accompaniment. Finally, we discuss the integration of these offline accompaniment systems into a real-time system.

Original languageEnglish
Title of host publication41st International Computer Music Conference, ICMC 2015
Subtitle of host publicationLooking Back, Looking Forward - Proceedings
EditorsRichard Dudas
PublisherInternational Computer Music Association
Pages290-297
Number of pages8
ISBN (Electronic)0984527443, 9780984527441
StatePublished - 2015
Event41st International Computer Music Conference: Looking Back, Looking Forward, ICMC 2015 - Denton, United States
Duration: Sep 25 2015Oct 1 2015

Publication series

Name41st International Computer Music Conference, ICMC 2015: Looking Back, Looking Forward - Proceedings

Conference

Conference41st International Computer Music Conference: Looking Back, Looking Forward, ICMC 2015
Country/TerritoryUnited States
CityDenton
Period09/25/1510/1/15

Fingerprint

Dive into the research topics of 'Improving and adapting finite state transducer methods for musical accompaniment'. Together they form a unique fingerprint.

Cite this