Machine Annotation of Traditional Irish Dance Music - Paperback

by Bryan Duggan (Author)

Estimates put the canon of traditional Irish dance tunes at at least seven thousand compositions. Given this diversity, a common problem faced by musicians and ethnomusicologists is identifying tunes from recordings. This work attempts to solve this problem by developing a Content Based Music Information Retrieval (CBMIR) system adapted to the characteristics of traditional Irish dance music. Included is a comprehensive review of the domain of traditional Irish music and three chapters of related work in the fields of feature extraction, melodic similarity and music information retrieval. A new software system is presented called MATT2 (Machine Annotation of Traditional Tunes) whose goal is to annotate recordings of traditional Irish dance music with useful metadata. A new algorithm is also presented called TANSEY (Turn ANnotation from SEts using SimilaritY profiles) that annotates sets of tunes played segue as is the custom in traditional Irish dance music.

Author Biography

Bryan Duggan is a lecturer in the School of Computing in the Dublin Institute of Technology. He received his PhD on the topic of "Machine Annotation of Traditional Irish Dance Tunes" in October 2009. This work proposed new algorithms and systems for the analysis of recordings of traditional Irish dance music and matching recordings to ground truth transcriptions. He has been teaching courses on Games Programming and Music Technology for the past six years. Bryan is also the author of TunePal Mobile and tunepal.org - free, open source music tools for traditional musicians. He is also an accomplished traditional flute player.