Annotation and analysis of overlapping speech in political interviews

Martine Adda-Decker (1) , Claude Barras (1) , Gilles Adda (1) , Patrick Paroubek (1) , Philippe Boula de Mareüil (1) , Benoit Habert (2)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 ICAR - Interactions, Corpus, Apprentissages, Représentations

Looking for a better understanding of spontaneous speech-related phenomena and to improve automatic speech recognition (ASR), we present here a study on the relationship between the occurrence of overlapping speech segments and disfluencies (filled pauses, repetitions, revisions) in political interviews. First we present our data, and our overlap annotation scheme. We detail our choice of overlapping tags and our definition of disfluencies; the observed ratios of the different overlapping tags are examined, as well as their correlation with of the speaker role and propose two measures to characterise speakers' interacting attitude: the attack/resist ratio and the attack density. We then study the relationship between the overlapping speech segments and the disfluencies in our corpus, before concluding on the perspectives that our experiments offer.

Domaines: Informatique [cs]

Martine Adda-Decker, Claude Barras, Gilles Adda, Patrick Paroubek, Philippe Boula de Mareüil, et al.. Annotation and analysis of overlapping speech in political interviews. LREC 2008, May 2008, Marrakech, Morocco. ⟨hal-01690328⟩