Pearce, Marcus T.; Müllensiefen, Daniel and Wiggins, Geraint. 2010. Melodic Grouping in Music Information Retrieval: New Methods and Applications. In: Zbigniew W. Ras and Alicja Wieczorkowska, eds. Advances in Music Information Retrieval Advances in Music Information Retrieval. 274 Berlin and New York: Springer, pp. 365-390. ISBN 978-3-642-11673-5 [Book Section]

Text AMIR_PearceMullensiefenWiggins_2010.pdf - Accepted Version Permissions: GRO Registered Users Only Download (184kB)

Abstract or Description

We introduce the MIR task of segmenting melodies into phrases, summarise the musicological and psychological background to the task and review existing computational methods before presenting a new model, IDyOM, for melodic segmentation based on statistical learning and information-dynamic analysis. The performance of the model is compared to several existing algorithms in predicting the annotated phrase boundaries in a large corpus of folk music. The results indicate that four algorithms produce acceptable results: one of these is the IDyOM model which performs much better than naive statistical models and approaches the performance of the best-performing rule-based models. Further slight performance improvement can be obtained by combining the output of the four algorithms in a hybrid model, although the performance of this model is moderate at best, leaving a great deal of room for improvement on this task.

Item Type:	Book Section
Departments, Centres and Research Units:	Psychology
Dates:	Date Event 2010 Published
Item ID:	5391
Date Deposited:	28 Mar 2011 10:42
Last Modified:	29 Apr 2020 15:30
URI:	https://research.gold.ac.uk/id/eprint/5391

View statistics for this item...

Edit Record (login required)