59 citations · 182 across the 13 of their papers we have counts for
4 papers · 1 filter
Dilated convolution with learnable spacings
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Recent works indicate that convolutional neural networks (CNN) need large receptive fields (RF) to compete with visual transformers and their attention mechanism. In CNNs, RFs can…
End-to-end acoustic modelling for phone recognition of young readers
Lucile Gelin, Morgane Daniel, Julien Pinquier +1
Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and lingui…
Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning
Thomas Pellegrini, Timothée Masquelier
Multi-label audio tagging consists of assigning sets of tags to audio recordings. At inference time, thresholds are applied on the confidence scores outputted by a probabilistic cl…
Comparison of semi-supervised deep learning algorithms for audio classification
Léo Cances, Etienne Labbé, Thomas Pellegrini
In this article, we adapted five recent SSL methods to the task of audio classification. The first two methods, namely Deep Co-Training (DCT) and Mean Teacher (MT), involve two col…