Reliability of Lexical and Prosodic Cues in two Real-life Spoken Dialog Corpora


L. Devillers (1), I. Vasilescu(2)

(1) LIMSI-CNRS , BP133, 91 403 Orsay Cedex, France - devil@limsi.fr; (2) LTCI-ENST, 46, rue Barrault, 75013 Paris, France - vasilescu@tsi.enst.fr




The present research focuses on analyzing and detecting emotions in speech as re vealed by task-dependent spoken dialogs corpora. Previously, we have conducted s everal experiments on a real-life corpus in order to develop a reliable annotati on method and to detect lexical and prosodic cues correlated to the main emotion class. In this paper we evaluate both the robustness of the annotation scheme a nd of the lexical and prosodic cues by testing them on a new corpus. This work i s carried out in the context of the Amities project in which spoken dialog syste ms for call center services are being developed.


emotion detection, real-life call centers database, prosodic and lexical cues

Language(s) N/A
Full Paper