Picture for Thomas Pellegrini

Thomas Pellegrini

IRIT-SAMoVA

Audio classification with Dilated Convolution with Learnable Spacings

Add code
Sep 25, 2023
Viaarxiv icon

Multilingual Audio Captioning using machine translated data

Add code
Sep 14, 2023
Viaarxiv icon

CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding

Add code
Sep 01, 2023
Viaarxiv icon

Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?

Add code
Aug 29, 2023
Viaarxiv icon

Adapting a ConvNeXt model to audio classification on AudioSet

Add code
Jun 01, 2023
Viaarxiv icon

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation

Add code
Jun 01, 2023
Figure 1 for Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Figure 2 for Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Figure 3 for Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Figure 4 for Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Viaarxiv icon

Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer

Add code
May 02, 2023
Viaarxiv icon

Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates

Add code
Nov 14, 2022
Viaarxiv icon

Audio-video fusion strategies for active speaker detection in meetings

Add code
Jun 09, 2022
Figure 1 for Audio-video fusion strategies for active speaker detection in meetings
Figure 2 for Audio-video fusion strategies for active speaker detection in meetings
Figure 3 for Audio-video fusion strategies for active speaker detection in meetings
Figure 4 for Audio-video fusion strategies for active speaker detection in meetings
Viaarxiv icon

Dilated convolution with learnable spacings

Add code
Dec 07, 2021
Figure 1 for Dilated convolution with learnable spacings
Figure 2 for Dilated convolution with learnable spacings
Figure 3 for Dilated convolution with learnable spacings
Figure 4 for Dilated convolution with learnable spacings
Viaarxiv icon