Annotator subjectivity in harmony annotations of popular music
Top Cited Papers
Open Access
- 1 March 2019
- journal article
- research article
- Published by Taylor & Francis Ltd in Journal of New Music Research
- Vol. 48 (3), 232-252
- https://doi.org/10.1080/09298215.2019.1613436
Abstract
Reference annotation datasets containing harmony annotations are at the core of a wide range of studies in music information retrieval (MIR) and related fields. The majority of these datasets contain single reference annotations describing the harmony of each piece. Nevertheless, studies showing differences among annotators in many other MIR tasks make the notion of a single ‘ground-truth’ reference annotation a tenuous one. In this paper, we introduce and analyse the Chordify Annotator Subjectivity Dataset (CASD) containing chord labels for 50 songs from 4 expert annotators in order to gain a better understanding of the differences between annotators in their chord label choice. Our analysis reveals that annotators use distinct chord-label vocabularies, with low chord-label overlap across all annotators. Between annotators, we find only 73 percent overlap on average for the traditional major–minor vocabulary and 54 percent overlap for the most complex chord labels. A factor analysis reveals the relative importance of triads, sevenths, inversions and other musical factors for each annotator on their choice of chord labels and reported difficulty of the songs. Our results further substantiate the existence of a harmonic ‘subjectivity ceiling’: an upper bound for evaluations in computational harmony research. Current state-of-the-art chord-estimation systems perform beyond this subjectivity ceiling by about 10 percent. This suggests that current ACE algorithms are powerful enough to tune themselves to particular annotators' idiosyncrasies. Overall, our results show that annotator subjectivity is an important factor in harmonic transcriptions, which should inform future studies into harmony perception and computational models of harmony.Keywords
This publication has 25 references indexed in Scilit:
- A corpus analysis of rock harmonyPopular Music, 2011
- Evaluation of Audio Beat Tracking and Music Tempo Extraction AlgorithmsJournal of New Music Research, 2007
- Audio Key Finding: Considerations in System Design and Case Studies on Chopin's 24 PreludesEURASIP Journal on Advances in Signal Processing, 2006
- Reliability in Content Analysis.Human Communication Research, 2004
- Determining the number of components from the matrix of partial correlationsPsychometrika, 1976
- An Investigation of the Parallel Analysis Criterion for Determining the Number of Common FactorsMultivariate Behavioral Research, 1975
- Estimating the Reliability, Systematic Error and Random Error of Interval DataEducational and Psychological Measurement, 1970
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960
- The development of hierarchical factor solutionsPsychometrika, 1957