59 citations · 182 across the 13 of their papers we have counts for
16 papers
Adapting a ConvNeXt model to audio classification on AudioSet
Thomas Pellegrini, Ismail Khalfaoui-Hassani, Etienne Labbé +1
In computer vision, convolutional neural networks (CNN) such as ConvNeXt, have been able to surpass state-of-the-art transformers, partly thanks to depthwise separable convolutions…
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or…
Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer
Etienne Labbé, Julien Pinquier, Thomas Pellegrini
In this work, we propose to study the performance of a model trained with a sentence embedding regression loss component for the Automated Audio Captioning task. This task aims to…
Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
Automatic Audio Captioning (AAC) is the task that aims to describe an audio signal using natural language. AAC systems take as input an audio signal and output a free-form text sen…
Audio-video fusion strategies for active speaker detection in meetings
Lionel Pibre, Francisco Madrigal, Cyrille Equoy +4
Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In thi…
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…
Low-activity supervised convolutional spiking neural networks applied to speech commands recognition
Thomas Pellegrini, Romain Zimmer, Timothée Masquelier
Deep Neural Networks (DNNs) are the current state-of-the-art models in many speech related tasks. There is a growing interest, though, for more biologically realistic, hardware fri…
PCEDNet : A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds
Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini +3
In recent years, Convolutional Neural Networks (CNN) have proven to be efficient analysis tools for processing point clouds, e.g., for reconstruction, segmentation and classificati…
Technical report: supervised training of convolutional spiking neural networks with PyTorch
Romain Zimmer, Thomas Pellegrini, Srisht Fateh Singh +1
Recently, it has been shown that spiking neural networks (SNNs) can be trained efficiently, in a supervised manner, using backpropagation through time. Indeed, the most commonly us…
Evaluation of post-processing algorithms for polyphonic sound event detection
Leo Cances, Patrice Guyot, Thomas Pellegrini
Sound event detection (SED) aims at identifying audio events (audio tagging task) in recordings and then locating them temporally (localization task). This last task ends with the…
Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection
Thomas Pellegrini, Léo Cances
The design of new methods and models when only weakly-labeled data are available is of paramount importance in order to reduce the costs of manual annotation and the considerable h…
The Airbus Air Traffic Control speech recognition 2018 challenge: towards ATC automatic transcription and call sign detection
Thomas Pellegrini, Jérôme Farinas, Estelle Delpech +1
In this paper, we describe the outcomes of the challenge organized and run by Airbus and partners in 2018. The challenge consisted of two tasks applied to Air Traffic Control (ATC)…
Densely Connected CNNs for Bird Audio Detection
Thomas Pellegrini
Detecting bird sounds in audio recordings automatically, if accurate enough, is expected to be of great help to the research community working in bio- and ecoacoustics, interested…