Enhancing the accessibility of hearing impaired to video content through fully automatic dynamic captioning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Enhancing the accessibility of hearing impaired to video content through fully automatic dynamic captioning

Résumé

In this paper we introduce an automatic subtitle positioning approach designed to enhance the video accessibility of deaf and hearing impaired people to multimedia documents. By using a dynamic subtitle and captioning approach, which exploits various computer vision techniques, including face detection, tracking and recognition, video temporal segmentation into shots and scenes and active speaker recognition, we are able to position each video subtitle segment in the near vicinity of the active speaker. The experimental evaluation performed on 30 video elements validates our approach with average F1-scores superior to 92%.
Fichier non déposé

Dates et versions

hal-02468749 , version 1 (06-02-2020)

Identifiants

Citer

Tapu Ruxandra, Mocanu Bogdan, Titus Zaharia. Enhancing the accessibility of hearing impaired to video content through fully automatic dynamic captioning. EHB 2019: 7th International Conference on E-Health and Bioengineering, Nov 2019, Iasi, Romania. pp.1-4, ⟨10.1109/EHB47216.2019.8970038⟩. ⟨hal-02468749⟩
31 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More