8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Prosodic Cues for Emotion Characterization in Real-Life Spoken Dialogs

Laurence Devillers (1), Ioana Vasilescu (2)

(1) LIMSI-CNRS, France
(2) ENST-CNRS, France

This paper reports on an analysis of prosodic cues for emotion characterization in 100 natural spoken dialogs recorded at a telephone customer service center. The corpus annotated with task-dependent emotion tags which were validated by a perceptual test. Two F0 range parameters, one at the sentence level and the other at the subsegment level, emerge as the most salient cues for emotion classification. These parameters can differentiate between negative emotion ( irritation/anger, anxiety/fear) and neutral attitude and confirm trends illustrated by the perceptual experiment.

Full Paper

Bibliographic reference.  Devillers, Laurence / Vasilescu, Ioana (2003): "Prosodic cues for emotion characterization in real-life spoken dialogs", In EUROSPEECH-2003, 189-192.