Title :
Understanding Effects of Subjectivity in Measuring Chord Estimation Accuracy
Author :
Yizhao Ni ; McVicar, Matt ; Santos-Rodriguez, R. ; De Bie, Tijl
Author_Institution :
Dept. of Eng. Math., Univ. of Bristol, Bristol, UK
Abstract :
To assess the performance of an automatic chord estimation system, reference annotations are indispensable. However, owing to the complexity of music and the sometimes ambiguous harmonic structure of polyphonic music, chord annotations are inherently subjective, and as a result any derived accuracy estimates will be subjective as well. In this paper, we investigate the extent of the confounding effect of subjectivity in reference annotations. Our results show that this effect is important, and they affect different types of automatic chord estimation systems in different ways. Our results have implications for research on automatic chord estimation, but also on other fields that evaluate performance by comparing against human provided annotations that are confounded by subjectivity.
Keywords :
audio signal processing; information retrieval; music; ambiguous harmonic structure; automatic chord estimation system; chord annotations; chord estimation accuracy; human provided annotations; polyphonic music; reference annotations; subjectivity evaluation; Complexity theory; Hamming distance; Information retrieval; Learning systems; Music; Music information retrieval; Subjectivity evaluation; automatic chord estimation; music information retrieval; sequence crowd learning;
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
DOI :
10.1109/TASL.2013.2280218