In this paper, we describe systems that were developed for the Open Performance Sub-Challenge of the INTERSPEECH 2009 Emotion Challenge. We participate in both two-class and five-class emotion detection. For the two-class problem, the best performance is obtained by logistic regression fusion of three systems. These systems use short- and long-term speech features. Fusion allowed to an absolute improvement of 2.6% on the unweighted recall value compared with . For the five-class problem, we submitted two individual systems: cepstral GMM vs. long-term GMM-UBM. The best result comes from a cepstral GMM and produces an absolute improvement of 3.5% compared to .
Bibliographic reference. Dumouchel, Pierre / Dehak, Najim / Attabi, Yazid / Dehak, Réda / Boufaden, Narjès (2009): "Cepstral and long-term features for emotion recognition", In INTERSPEECH-2009, 344-347.