Audio classification with Dilated Convolution with Learnable Spacings - Signaux et Images
Conference Papers Year : 2023

Audio classification with Dilated Convolution with Learnable Spacings

Abstract

Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation. Its interest has recently been demonstrated in computer vision (ImageNet classification and downstream tasks). Here, we show that DCLS is also useful for audio tagging using the AudioSet classification benchmark. We took two state-of-the-art convolutional architectures using depthwise separable convolutions (DSC), ConvNeXt and ConvFormer, and a hybrid one using attention in addition, FastViT, and drop-in replaced all the DSC layers by DCLS ones. This significantly improved the mean average precision (mAP) with the three architectures without increasing the number of parameters and with only a low cost on the throughput. The method code is based on PyTorch and is available at https://github.com/K-H-Ismail/DCLS-Audio.
Fichier principal
Vignette du fichier
dcls_audioset.pdf (212.37 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04314269 , version 1 (29-11-2023)

Licence

Identifiers

  • HAL Id : hal-04314269 , version 1

Cite

Ismail Khalfaoui-Hassani, Timothée Masquelier, Thomas Pellegrini. Audio classification with Dilated Convolution with Learnable Spacings. NeurIPS 2023 - Workshop on Machine Learning for Audio, Dec 2023, New Orleans, United States. ⟨hal-04314269⟩
193 View
43 Download

Share

More