Discriminatively trained recurrent neural networks for continuous dimensional emotion recognition from audio

  • Continuous dimensional emotion recognition from audio is a sequential regression problem, where the goal is to maximize correlation between sequences of regression outputs and continuous-valued emotion contours, while minimizing the average deviation. As in other domains, deep neural networks trained on simple acoustic features achieve good performance on this task. Yet, the usual squared error objective functions for neural network training do not fully take into account the above-named goal. Hence, in this paper we introduce a technique for the discriminative training of deep neural networks using the concordance correlation coefficient as cost function, which unites both correlation and mean squared error in a single differentiable function. Results on the MediaEval 2013 and AV+EC 2015 Challenge data sets show that the proposed method can significantly improve the evaluation criteria compared to standard mean squared error training, both in the music and speech domains.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Felix Weninger, Fabien Ringeval, Erik Marchi, Björn SchullerORCiDGND
URN:urn:nbn:de:bvb:384-opus4-720893
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/72089
URL:https://www.ijcai.org/Abstract/16/313
ISBN:9781577357766OPAC
Parent Title (English):Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, New York, NY, USA, 9-15 July 2016, volume 3
Publisher:AAAI Press / International Joint Conferences on Artificial Intelligence
Place of publication:Palo Alto, CA
Editor:Subbarao Kambhampati
Type:Conference Proceeding
Language:English
Year of first Publication:2016
Publishing Institution:Universität Augsburg
Release Date:2020/03/12
First Page:2196
Last Page:2202
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Embedded Intelligence for Health Care and Wellbeing
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):Deutsches Urheberrecht