This item is available under a Creative Commons License for non-commercial use only
1.2 COMPUTER AND INFORMATION SCIENCE
Music making and listening practices increasingly rely on techno logy,and,asaconsequence,techniquesdevelopedinmusicinformation retrieval (MIR) research are more readily available to end users, in par ticular via online tools and smartphone apps. However, the majority of MIRresearchfocusesonWesternpopandclassicalmusic,andthusdoes not address speciﬁcities of other musical idioms. Irishtraditionalmusic(ITM)ispopularacrosstheglobe,withregular sessionsorganisedonallcontinents. ITMisadistinctivemusicalidiom, particularly in terms of heterophony and modality, and these character istics can constitute challenges for existing MIR algorithms. The bene ﬁtsofdevelopingMIRmethodsspeciﬁcallytailoredtoITMisevidenced by Tunepal, a query-by-playing tool that has become popular among ITM practitioners since its release in 2009. As of today, Tunepal is the state of the art for tune recognition in ITM. The research in this thesis addresses existing limitations of Tunepal. The main goal is to ﬁnd solutions to add key-invariance to the tune re cognitionsystem,animportantfeaturethatiscurrentlymissinginTune pal. Techniques from digital signal processing and machine learning are used and adapted to the speciﬁcities of ITM to extract harmonic iv and temporal features, respectively with improvements on existing key detection methods, and a novel method for rhythm classiﬁcation. These featuresarethenusedtodevelopakey-invarianttunerecognitionsystem that is computationally efﬁcient while maintaining retrieval accuracy to a comparable level to that of the existing system.
Beauguitte, P. (2019) Music Information Retrieval for Irish Traditional Music Automatic Analysis of Harmonic, Rhythmic, and Melodic Features for Efﬁcient Key-Invariant Tune Recognition, Doctoral Thesis, Technological University Dublin. doi:10.21427/7hkk-p423