MEG Encoding using Neural Language & Speech Models and Shared Context Semantics in Listening Stories

We investigate if speech models outperform language models during speech-evoked brain activity, if LM and SM combine new word representation with previous context, and what are time of information is shared between them.

Domaines

Neurosciences [q-bio.NC] Machine Learning [stat.ML]

Fichier principal

OotaTrouvainAlexandreHinaut_SNL2023_Poster_HAL.pdf (2.3 Mo)

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

Xavier Hinaut : Connectez-vous pour contacter le contributeur

https://hal.science/hal-04401769

Soumis le : mercredi 17 janvier 2024-22:53:41

Dernière modification le : mardi 23 janvier 2024-10:55:12

Dates et versions

hal-04401769 , version 1 (17-01-2024)

Identifiants

HAL Id : hal-04401769 , version 1

Citer

Subba Reddy Oota, Nathan Trouvain, Gaël Jobard, Frédéric Alexandre, Xavier Hinaut. MEG Encoding using Neural Language & Speech Models and Shared Context Semantics in Listening Stories. SNL 2023 - Society for the Neurobiology of Language, Oct 2023, Marseille, France. . ⟨hal-04401769⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CNRS INRIA INRIA2 ANR

28 Consultations

7 Téléchargements