Sciweavers

Share
ML
2006
ACM

Using duration models to reduce fragmentation in audio segmentation

9 years 11 months ago
Using duration models to reduce fragmentation in audio segmentation
We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Markov Chain Monte Carlo methods; in particular, we introduce a modification to Wolff's algorithm to make it applicable to a segment classification model with an arbitrary duration prior. We apply this to a collection of pop songs, and show experimentally that the generated segmentations suffer much less from fragmentation than those produced by segmentation algorithms based on clustering, and are closer to an expert listener's annotations, as evaluated by two different performance measures. Keywords Segmentation . Duration prior . MCMC . Gibbs sampling . Wolff algorithm
Samer A. Abdallah, Mark B. Sandler, Christophe Rho
Added 14 Dec 2010
Updated 14 Dec 2010
Type Journal
Year 2006
Where ML
Authors Samer A. Abdallah, Mark B. Sandler, Christophe Rhodes, Michael Casey
Comments (0)
books