Overlapping sound event detection with supervised Nonnegative Matrix Factorization

Victor Bisot; Slim Essid; Gaël Richard

ICASSP 2017accepted0 citations

Overlapping sound event detection with supervised Nonnegative Matrix Factorization

Abstract

In this paper we propose a supervised Nonnegative Matrix Factorization (NMF) model for overlapping sound event detection in real life audio. We start by highlighting the usefulness of non-euclidean NMF to learn representations for detecting and classifying acoustic events in a multi-label setting. Then, we propose to learn a classifier and the NMF decomposition in a joint optimization problem. This is done with a general β-divergence version of the nonnegative task-driven dictionary learning model. An experimental evaluation is performed on the development set of the DCASE 2016 task3 challenge. The proposed supervised NMF-based system improves performance over the baseline and the submitted systems.

BibTeX

@inproceedings{icassp2017_overlappingsound,
  title = {Overlapping sound event detection with supervised Nonnegative Matrix Factorization},
  author = {Victor Bisot and Slim Essid and Gaël Richard},
  booktitle = {ICASSP 2017},
  year = {2017}
}