Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio

Weninger, Felix; Ringeval, Fabien; Marchi, Erik; Schuller, Björn W.

Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio

Felix Weninger, Fabien Ringeval, Erik Marchi, Björn W. Schuller

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2196-2201.

Abstract

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.

Felix Weninger, Fabien Ringeval, Erik Marchi, and Björn W. Schuller. 2016. Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2196–2201. https://ijcai.org/proceedings/2016/313

@inproceedings{ijcai2016p313,
  title     = {Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio},
  author    = {Weninger, Felix and Ringeval, Fabien and Marchi, Erik and Schuller, Björn W.},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {2196--2201},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/313},
}

TY  - CPAPER
TI  - Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio
AU  - Weninger, Felix
AU  - Ringeval, Fabien
AU  - Marchi, Erik
AU  - Schuller, Björn W.
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 2196
EP  - 2201
UR  - https://ijcai.org/proceedings/2016/313
ER  -