Automatic chord label personalization through deep learning of shared harmonic interval profiles

Koops, Hendrik Vincent; Haas, Wolfgang; Bransen, Jeroen; Volk, Anja

doi:10.1007/s00521-018-3703-y

Cited by 15 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chord-label estimation performances beyond a subjectivity ceiling suggest that stateof-the-art ace systems are starting to tune themselves to a particular subjective annotation and could also be powerful enough for chord-label personalisation. In fact, a first approach to such a system has already been introduced by Koops, de Haas, Bransen, and Volk (2017), showing that chord labels can be tuned to an annotator's specific vocabulary from a representation shared by multiple annotators.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Annotator subjectivity in harmony annotations of popular music

Koops

Haas²,

Burgoyne

et al. 2019

Journal of New Music Research

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Annotator subjectivity in harmony annotations of popular music

Koops

Haas²,

Burgoyne

et al. 2019

Journal of New Music Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Subsequently, we compare DECIBEL's chord sequences to the sequences estimated by the audio ACE system only. We experiment with twelve state-of-theart audio ACE systems: the submissions for the MIREX ACE competitions from 2017-2020 and the Chordify algorithm (based on Koops et al (2017), version of 2017).…”

Section: Ace On Audiomentioning

confidence: 99%

Improving Audio Chord Estimation by Alignment and Integration of Crowd-Sourced Symbolic Music

Odekerken

Koops

Volk

2021

Transactions of the International Society for Music Information Retrieval

Self Cite

View full text Add to dashboard Cite

“…Furthermore, annotations are largely prone to human subjectivity, with experts disagreeing in the annotations (Ni et al, 2013;Koops et al, 2017). Evaluation of the algorithms suffers from some inherent methodological pitfalls that make difficult to reliably evaluate and compare the behavior of ACE algorithm (Humphrey and Bello, 2015).…”

Section: Taking Into Account Human Subjectivitymentioning

confidence: 99%