Audio classification with Dilated Convolution with Learnable Spacings - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Audio classification with Dilated Convolution with Learnable Spacings

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Licence

Paternité

Identifiants

  • HAL Id : hal-04314269 , version 1

Citer

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⟩
108 Consultations
16 Téléchargements

Partager

Gmail Facebook X LinkedIn More