Acoustic measures characterizing anger across corpora collected in artificial or natural context

Marie Tahon (1) , Laurence Devillers (1)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

This paper aims at studying differences between acoustic manifestations of anger across corpora collected in artificial, manipulated or natural context. It aims further at finding measures of naturalness in emotive corpora. Evaluating the degree of naturalness of a corpus can be challenging unless given knowledge upon the task. In corpora consisting of rather acted data, anger is often stronger; we believe that a kind of distance can be computed between anger and the overall corpus data. Such a distance is introduced in this work and evaluated with state-of-art acoustic descriptors in 3 collected corpora. We show the observed differences between the acoustic features obtained with anger samples in these different contexts and propose measures of naturalness.

Mots clés: Emotion detection; anger; naturalness; prototypical emotion

Domaines: Intelligence artificielle [cs.AI]

Marie Tahon, Laurence Devillers. Acoustic measures characterizing anger across corpora collected in artificial or natural context. Speech Prosody, 2010, Chicago, United States. ⟨hal-01768783⟩