Loading...
The Signals and Images department carries out researches related to image processing, sound analysis, 3D geometry generally dealing with massive digital data. The aim is to understand their constitution, identify their content, extract their semantic and build an efficient model of these data. From such models, we may synthetize new data, extract the relevant information, or encode and transmit them.
For more information, consult the Signals and Images department presentation on the IRIT website.
Latest full text publications
-
Marvin Lavechin, Marianne Métais, Hadrien Titeux, Alodie Boissonnet, Jade Copet, et al.. Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation. IEEE Automatic Speech Recognition and Understanding (ASRU 2023 ), IEEE, Dec 2023, Taipei, Taiwan. pp.1--7. ⟨hal-04247647⟩
-
Sebastião Quintas, Mathieu Balaguer, Julie Mauclair, Virginie Woisard, Julien Pinquier. Can we use speaker embeddings on spontaneous speech obtained from medical conversations to predict intelligibility?. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2023), IEEE, Dec 2023, Taipei, Taiwan. à paraître. ⟨hal-04230836⟩
-
-
-
-
-
Maxime Cordeil, Thomas Billy, Nicolas Mellado, Loic Barthe, Nadine Couture, et al.. ImmersiveIML – Immersive interactive machine learning for 3D point cloud classification: the neural network at your fingertips. IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct 2023), Oct 2023, Sydney, Australia. à paraître. ⟨hal-04246601⟩
-
-
-
Carine Calastrenc, Christine Rendu, Nicolas Poirier, François Baleux, Pierre Campmajo, et al.. Prospecter les montagnes autrement : Télédétection Archéologique en Haute et Moyenne Montagne (TAHMM). Séminaire de laboratoire TRACES (2023), Laboratoire TRACES (UMR 5608) - Toulouse, Oct 2023, Toulouse, France. ⟨hal-04244922⟩
Documents
1 308
Distribution per document type