Title
Sequential Complexity as a Descriptor for Musical Similarity
Abstract
We propose string compressibility as a descriptor of temporal structure in audio, for the purpose of determining musical similarity. Our descriptors are based on computing track-wise compression rates of quantized audio features, using multiple temporal resolutions and quantization granularities. To verify that our descriptors capture musically relevant information, we incorporate our descriptors into similarity rating prediction and song year prediction tasks. We base our evaluation on a dataset of 15 500 track excerpts of Western popular music, for which we obtain 7 800 web-sourced pairwise similarity ratings. To assess the agreement among similarity ratings, we perform an evaluation under controlled conditions, obtaining a rank correlation of 0.33 between intersected sets of ratings. Combined with bag-of-features descriptors, we obtain performance gains of 31.1% and 10.9% for similarity rating prediction and song year prediction. For both tasks, analysis of selected descriptors reveals that representing features at multiple time scales benefits prediction accuracy.
Year
DOI
Venue
2014
10.1109/TASLP.2014.2357676
Audio, Speech, and Language Processing, IEEE/ACM Transactions  
Keywords
DocType
Volume
audio coding,data compression,music,quantisation (signal),Web-sourced pairwise similarity ratings,Western popular music,audio temporal structure,bag-of-feature descriptors,multiple temporal resolutions,multiple time scale benefit prediction accuracy,musical similarity descriptor,quantization granularities,quantized audio features,rank correlation,sequential complexity,similarity rating prediction,song year prediction tasks,string compressibility,track-wise compression rates,Music content analysis,musical similarity measures,time series complexity
Journal
22
Issue
ISSN
Citations 
12
2329-9290
2
PageRank 
References 
Authors
0.41
45
3
Name
Order
Citations
PageRank
Peter Foster1131.64
Matthias Mauch238126.97
Simon Dixon31164107.57