Improving Speaker Diarization of TV Series using Talking-Face Detection and Clustering - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Improving Speaker Diarization of TV Series using Talking-Face Detection and Clustering

Résumé

While successful on broadcast news, meetings or telephone conversation, state-of-the-art speaker diarization techniques tend to perform poorly on TV series or movies. In this paper, we propose to rely on state-of-the-art face clustering techniques to guide acoustic speaker diarization. Two approaches are tested and evaluated on the rst season of Game Of Thrones TV series. The second (better) approach relies on a novel talking-face detection module based on bidirectional long short-term memory recurrent neural network. Both audio-visual approaches outperform the audio only baseline. A detailed study of the behavior of these approaches is also provided and paves the way to future improvements.
Fichier non déposé

Dates et versions

hal-01836453 , version 1 (12-07-2018)

Identifiants

  • HAL Id : hal-01836453 , version 1

Citer

Hervé Bredin, Gregory Gelly. Improving Speaker Diarization of TV Series using Talking-Face Detection and Clustering. ACM Multimedia 2016, ACM, Jan 2016, Amsterdam, Netherlands. ⟨hal-01836453⟩
44 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More