Nonnegative Feature Learning Methods for Acoustic Scene Classification

Abstract : This paper introduces improvements to nonnegative feature learning-based methods for acoustic scene classification. We start by introducing modifications to the task-driven nonnegative matrix factorization algorithm. The proposed adapted scaling algorithm improves the generalization capability of task-driven nonneg-ative matrix factorization for the task. We then propose to exploit simple deep neural network architecture to classify both low level time-frequency representations and unsupervised nonnegative matrix factorization activation features independently. Moreover, we also propose a deep neural network architecture that exploits jointly unsupervised nonnegative matrix factorization activation features and low-level time frequency representations as inputs. Finally, we present a fusion of proposed systems in order to further improve performance. The resulting systems are our submission for the task 1 of the DCASE 2017 challenge.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-01636627
Contributor : Romain Serizel <>
Submitted on : Thursday, November 16, 2017 - 5:37:24 PM
Last modification on : Wednesday, April 3, 2019 - 1:22:59 AM
Document(s) archivé(s) le : Saturday, February 17, 2018 - 5:05:23 PM

File

nonnegative-feature-learning.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01636627, version 1

Citation

Victor Bisot, Romain Serizel, Slim Essid, Gaël Richard. Nonnegative Feature Learning Methods for Acoustic Scene Classification. DCASE 2017 - Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2017, Munich, Germany. ⟨hal-01636627⟩

Share

Metrics

Record views

576

Files downloads

66