10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Combining Spectral and Prosodic Information for Emotion Recognition in the Interspeech 2009 Emotion Challenge

Iker Luengo, Eva Navas, Inmaculada Hernáez

University of the Basque Country, Spain

This paper describes the system presented at the Interspeech 2009 Emotion Challenge. It relies on both spectral and prosodic features in order to automatically detect the emotional state of the speaker. As both kinds of features have very different characteristics, they are treated separately, creating two sub-classifiers, one using the spectral features and the other one using the prosodic ones. The results of these two classifiers are then combined with a fusion system based on Support Vector Machines.

Full Paper

Bibliographic reference.  Luengo, Iker / Navas, Eva / Hernáez, Inmaculada (2009): "Combining spectral and prosodic information for emotion recognition in the interspeech 2009 emotion challenge", In INTERSPEECH-2009, 332-335.