TY - GEN
T1 - Cross-corpus acoustic emotion recognition
T2 - 2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015
AU - Schuller, Bjorn
AU - Vlasenko, Bogdan
AU - Eyben, Florian
AU - Wollmer, Martin
AU - Stuhlsatz, Andre
AU - Wendemuth, Andreas
AU - Rigoll, Gerhard
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/2
Y1 - 2015/12/2
N2 - As the recognition of emotion from speech has matured to a degree where it becomes applicable in real-life settings, it is time for a realistic view on obtainable performances. Most studies tend to overestimation in this respect: acted data is often used rather than spontaneous data, results are reported on pre-selected prototypical data, and true speaker disjunctive partitioning is still less common than simple cross-validation. A considerably more realistic impression can be gathered by inter-set evaluation: we therefore show results employing six standard databases in a cross-corpora evaluation experiment. To better cope with the observed high variances, different types of normalization are investigated. 1.8 k individual evaluations in total indicate the crucial performance inferiority of inter- to intra-corpus testing.
AB - As the recognition of emotion from speech has matured to a degree where it becomes applicable in real-life settings, it is time for a realistic view on obtainable performances. Most studies tend to overestimation in this respect: acted data is often used rather than spontaneous data, results are reported on pre-selected prototypical data, and true speaker disjunctive partitioning is still less common than simple cross-validation. A considerably more realistic impression can be gathered by inter-set evaluation: we therefore show results employing six standard databases in a cross-corpora evaluation experiment. To better cope with the observed high variances, different types of normalization are investigated. 1.8 k individual evaluations in total indicate the crucial performance inferiority of inter- to intra-corpus testing.
KW - Cross-corpus
KW - Speech Emotion Recognition
UR - http://www.scopus.com/inward/record.url?scp=84964039917&partnerID=8YFLogxK
U2 - 10.1109/ACII.2015.7344612
DO - 10.1109/ACII.2015.7344612
M3 - Conference contribution
AN - SCOPUS:84964039917
T3 - 2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015
SP - 470
EP - 476
BT - 2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 September 2015 through 24 September 2015
ER -