Joint Generation of Captions and Subtitles with Dual Decoding - Traitement du Langage Parlé Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Joint Generation of Captions and Subtitles with Dual Decoding

François Buet
Josep Crego
  • Fonction : Auteur
Elise Bertin-Lemée
  • Fonction : Auteur
François Yvon

Résumé

As the amount of audiovisual content increases, the need to develop automatic captioning and subtitling solutions to match the expectations of a growing international audience appears as the only viable way to boost throughput and lower the related postproduction costs. Automatic captioning and subtitling often need to be tightly intertwined to achieve an appropriate level of consistency and synchronization with each other and with the video signal. In this work, we assess a dual decoding scheme to achieve a strong coupling between these two tasks and show how adequacy and consistency are increased, with virtually no additional cost in terms of model size and training complexity.
Fichier principal
Vignette du fichier
acl_iwslt_arxiv.pdf (272.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03666567 , version 1 (12-05-2022)

Identifiants

  • HAL Id : hal-03666567 , version 1

Citer

Jitao Xu, François Buet, Josep Crego, Elise Bertin-Lemée, François Yvon. Joint Generation of Captions and Subtitles with Dual Decoding. 19th International Conference on Spoken Language Translation (IWSLT 2022), May 2022, Dublin, Ireland. ⟨hal-03666567⟩
83 Consultations
37 Téléchargements

Partager

Gmail Facebook X LinkedIn More