Sciweavers

ICASSP
2011
IEEE

Evaluating music sequence models through missing data

12 years 7 months ago
Evaluating music sequence models through missing data
Building models of the structure in musical signals raises the question of how to evaluate and compare different modeling approaches. One possibility is to use the model to impute deliberatelyremoved patches of missing data, then to compare the model’s predictions with the part that was removed. We analyze a corpus of popular music audio represented as beat-synchronous chroma features, and compare imputation based on simple linear prediction to more complex models including nearest neighbor selection and shift-invariant probabilistic latent component analysis. Simple linear models perform best according to Euclidean distance, despite producing stationary results which are not musically meaningful. We therefore investigate alternate evaluation measures and observe that an entropy difference metric correlates better with our expectations for musically consistent reconstructions. Under this measure, the best-performing imputation algorithm reconstructs masked sections by choosing the n...
Thierry Bertin-Mahieux, Graham Grindlay, Ron J. We
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Thierry Bertin-Mahieux, Graham Grindlay, Ron J. Weiss, Daniel P. W. Ellis
Comments (0)