Cross-Corpus Classification of Realistic Emotions - Some Pilot Experiments

Eyben F, Batliner A, Schuller B, Seppi D, Steidl S (2010)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2010

Original Authors: Eyben Florian, Batliner Anton, Schuller Björn, Seppi Dino, Steidl Stefan

Pages Range: 77-82

Conference Proceedings Title: Proc. of theThird International Workshop on EMOTION (satellite of LREC): CORPORA FOR RESEARCH ON EMOTION AND AFFECT

Event location: Valetta MT

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Eyben10-CCO.pdf

Abstract

We use four speech databases with realistic, non-prompted emotions, and a large state-of-the-art acoustic feature vector, for cross-corpus classifications, in turn employing three databases for training and the fourth for testing. Categorical and continuous (dimensional) annotation is mapped onto a representation of valence with the three classes positive, neutral, and negative. This cross-corpus classification is compared with within corpus classifications. We interpret performance and most important features.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Eyben, F., Batliner, A., Schuller, B., Seppi, D., & Steidl, S. (2010). Cross-Corpus Classification of Realistic Emotions - Some Pilot Experiments. In LREC (Eds.), Proc. of theThird International Workshop on EMOTION (satellite of LREC): CORPORA FOR RESEARCH ON EMOTION AND AFFECT (pp. 77-82). Valetta, MT.

MLA:

Eyben, Florian, et al. "Cross-Corpus Classification of Realistic Emotions - Some Pilot Experiments." Proceedings of the Third International Workshop on EMOTION, Valetta Ed. LREC, 2010. 77-82.

BibTeX: Download