Skip to Main content Skip to Navigation
New interface
Conference papers

Latent and Adversarial Data Augmentation for Sound Event Detection and Classification

David Perera 1, 2, 3 Slim Essid 1, 2, 3 Gaël Richard 1, 2, 3 
Abstract : Invariance-based learning is a promising approach in deep learning. Among other benefits, it can mitigate the lack of diversity of available datasets and increase the interpretability of trained models. To this end, practitioners often use a consistency cost penalizing the sensitivity of a model to a set of carefully selected data augmentations. However, there is no consensus about how these augmentations should be selected. In this paper, we study the behavior of several augmentation strategies. We consider the task of sound event detection and classification for our experiments. In particular, we show that transformations operating on the internal layers of a deep neural network are beneficial for this task.
Document type :
Conference papers
Complete list of metadata
Contributor : David Perera Connect in order to contact the contributor
Submitted on : Wednesday, September 21, 2022 - 3:33:18 PM
Last modification on : Friday, November 18, 2022 - 3:35:48 PM


Files produced by the author(s)


  • HAL Id : hal-03782827, version 1



David Perera, Slim Essid, Gaël Richard. Latent and Adversarial Data Augmentation for Sound Event Detection and Classification. International workshop on Detection and Classiffication of Acoustic Scenes and Events (DCASE), Nov 2022, Nancy, France. ⟨hal-03782827⟩



Record views


Files downloads