Poster De Conférence Année : 2023

How to describe every sound automatically : Automated Audio Captioning

Comment décrire tous les sons automatiquement : Description Textuelle Automatique de l'Audio

Résumé

In the audio research field, the majority of machine learning systems focus on recognizing a limited number of sound events. However, when a machine interacts with real data, it must be able to handle much more varied and complex situations. To tackle this problem, annotators use natural language, which allows any sound information to be summarized. Automated Audio Captioning (AAC) was introduced recently to develop systems capable of automatically producing a description of any type of sound in text form. This task concerns all kinds of sound events such as environmental, urban, domestic sounds, sound effects, music or speech. This type of system could be used by people who are deaf or hard of hearing, and could improve the indexing of large audio databases.

Fichier principal
Vignette du fichier
RJCP2023_Poster.pdf (1.14 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04956664 , version 1 (19-02-2025)

Licence

Identifiants

  • HAL Id : hal-04956664 , version 1

Citer

Etienne Labbé, Thomas Pellegrini, Julien Pinquier. Comment décrire tous les sons automatiquement : Description Textuelle Automatique de l'Audio. Rencontre Jeunes Chercheurs en Paroles (RJCP) 2023, Nov 2023, Grenoble, France. 2023. ⟨hal-04956664⟩
32 Consultations
44 Téléchargements

Partager

  • More