Unsupervised Speaker Identification using Overlaid Texts in TV Broadcast

Johann Poignant (1) , Hervé Bredin (2) , Viet-Bac Le (3) , Laurent Besacier (4) , Claude Barras (2) , Georges Quénot (5)

1 LIG - Laboratoire d'Informatique de Grenoble
2 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
3 Vocapia Research [Orsay]
4 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
5 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]

We propose an approach for unsupervised speaker identification in TV broadcast videos, by combining acoustic speaker diarization with person names obtained via video OCR from overlaid texts. Three methods for the propagation of the overlaid names to the speech turns are compared, taking into account the co-occurence duration between the speaker clusters and the names provided by the video OCR and using a task-adapted variant of the TF-IDF information retrieval coefficient. These methods were tested on the REPERE dry-run evaluation corpus, containing 3 hours of annotated videos. Our best unsupervised system reaches a F-measure of 70.2% when considering all the speakers, and 81.7% if anchor speakers are left out. By comparison, a mono-modal, supervised speaker identification system with 535 speaker models trained on matching development data and additional TV and radio data only provided a 57.5% F-measure when considering all the speakers and 45.7% without anchor.

Mots clés: unsupervised speaker identification; multimodal fusion; speaker diarization; optical character recognition; reproducible results

Domaines: Recherche d'information [cs.IR]

Johann Poignant, Hervé Bredin, Viet-Bac Le, Laurent Besacier, Claude Barras, et al.. Unsupervised Speaker Identification using Overlaid Texts in TV Broadcast. Interspeech 2012 - Conference of the International Speech Communication Association, Sep 2012, Portland, OR, United States. 4p. ⟨hal-00767427⟩