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 [1]. 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 [2].
s B. Schüller, S. Steidl, and A. Batliner, The Interspeech 2009 Emotion Challenge, in Interspeech. Brighton, UK: ISCA, 2009. C.-Y. Lin and H-C.Wang, Language Identification Using Pitch Contour Information, in ICASSP, 2005, pp. 601604.
Cite as: Dumouchel, P., Dehak, N., Attabi, Y., Dehak, R., Boufaden, N. (2009) Cepstral and long-term features for emotion recognition. Proc. Interspeech 2009, 344-347, doi: 10.21437/Interspeech.2009-111
@inproceedings{dumouchel09_interspeech,
author={Pierre Dumouchel and Najim Dehak and Yazid Attabi and Réda Dehak and Narjès Boufaden},
title={{Cepstral and long-term features for emotion recognition}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={344--347},
doi={10.21437/Interspeech.2009-111}
}