Projects per year
Abstract
A recent review of the research literature evaluating music genre recognition (MGR) systems over the past two decades shows that most works (81\%) measure the capacity of a system to recognize genre by its classification accuracy. We show here, by implementing and testing three categorically different state-of-the-art MGR systems, that classification accuracy does not necessarily reflect the capacity of a system to recognize genre in musical signals. We argue that a more comprehensive analysis of behavior at the level of the music is needed to address the problem of MGR, and that measuring classification accuracy obscures the aim of MGR: to select labels indistinguishable from those a person would choose.
Original language | English |
---|---|
Journal | Journal of Intelligent Information Systems |
Volume | 41 |
Issue number | 3 |
Pages (from-to) | 371-406 |
Number of pages | 36 |
ISSN | 0925-9902 |
DOIs | |
Publication status | Published - 2013 |
Fingerprint
Dive into the research topics of 'Classification Accuracy Is Not Enough: On the Evaluation of Music Genre Recognition Systems'. Together they form a unique fingerprint.-
Greedy Sparse Approximation and the Automatic Description of Audio and Music Data
Sturm, B. L.
Technology and Production Independent Postdoc Center for Independent Research
01/01/2012 → …
Project: Research
-
CoSound
Christensen, M. G., Tan, Z., Jensen, S. H. & Sturm, B. L.
01/01/2012 → 31/12/2015
Project: Research
Activities
- 1 Talks and presentations in private or public companies
-
The Crisis of Evaluation in Music Information Retrieval
Bob L. Sturm (Lecturer)
13 Nov 2013Activity: Talks and presentations › Talks and presentations in private or public companies
File