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

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2016-January, Issue , 2016, Pages 2196-2202

  Weninger, Felix ^a   Ringeval, Fabien ^b   Marchi, Erik ^b   Schuller, Bjorn ^b,c  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b UNIVERSITY OF PASSAU   (Germany)

^c IMPERIAL COLLEGE LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; COST FUNCTIONS; ERRORS; MEAN SQUARE ERROR; NEURAL NETWORKS; SPEECH RECOGNITION;

CORRELATION COEFFICIENT; DEEP NEURAL NETWORKS; DIFFERENTIABLE FUNCTIONS; DISCRIMINATIVE TRAINING; EMOTION RECOGNITION; EVALUATION CRITERIA; NEURAL NETWORK TRAINING; OBJECTIVE FUNCTIONS;

RECURRENT NEURAL NETWORKS;

EID: 85006110321     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (27)

1. Eduardo Coutinho and Angelo Cangelosi. A neural network model for the prediction of musical emotions. In S. Nefti-Meziani and J. G. Grey, editors, Advances in Cognitive Systems, pages 331-368. IET Publisher, London, UK, 2010.
2. Florian Eyben, Martin Wöllmer, and Björn Schuller. A Multi-Task Approach to Continuous Five-Dimensional Affect Sensing in Natural Speech. ACM Transactions on Interactive Intelligent Systems, Special Issue on Affective Interaction in Natural Environments, 2 (1), March 2012. 29 pages.
3. Florian Eyben, Klaus Scherer, Björn Schuller, Johan Sundberg, Elisabeth André, Carlos Busso, Laurence Devillers, Julien Epps, Petri Laukka, Shrikanth Narayanan, and Khiet Truong. The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing. IEEE Transactions on Affective Computing, 2015. in press.
4. Felix A. Gers, Jürgen Schmidhuber, and Fred Cummins. Learning to forget: Continual prediction with LSTM. Neural Computation, 12 (10): 2451-2471, 2000.
5. Kun Han, Dong Yu, and Ivan Tashev. Speech Emotion Recognition Using Deep Neural Network and Extreme Learning Machine. In Proc. of INTERSPEECH, pages 223-227, Singapore, September 2014. ISCA.
6. Lang He, Dongmei Jiang, Le Yang, Ercheng Pei, Peng Wu, and Hichem Sahli. Multimodal Affective Dimension Prediction Using Deep Bidirectional Long Short-Term Memory Recurrent Neural Networks. In Proc. of AVEC, pages 73-80, Brisbane, Australia, October 2015. ACM.
7. Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, and Paris Smaragdis. Joint Opti-mization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. IEEE Transactions on Audio, Speech, and Language Processing, 23 (12): 2136-2147, December 2015.
8. Robert Jenke, Angelika Peer, and Martin Buss. A Comparison of Evaluation Measures for Emotion Recognition in Dimensional Space. In Proc. of ACII, pages 822-826, Geneva, Switzerland, September 2013. IEEE.
9. Markus Kächele, Patrick Thiam, Günther Palm, Friedhelm Schwenker, and Martin Schels. Ensemble methods for continuous affect recognition: Multimodality, temporality, and challenges. In Proc. of AVEC (held in conjunction with ACM MM), pages 9-16, Brisbane, Australia, October 2015. ACM.
10. Brian Kingsbury, Tara N. Sainath, and Hagen Soltau. Scalable minimum Bayes risk training of deep neural network acoustic models using distributed Hessian-free optimization. In Proc. of ICASSP, Kyoto, Japan, 2012.
11. Longfei Li, Yong Zhao, Dongmei Jiang, Yanning Zhang, Fengna Wang, I. Gonzalez, E. Valentin, and H. Sahli. Hybrid Deep Neural Network-Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition. In Proc. of ACII, pages 312-317, Geneva, Switzerland, September 2013. IEEE.
12. Lawrence I. Lin. A concordance correlation coefficient to evaluate reproducibility. Biometrics, 45 (1): 255-268, March 1989.
13. Soroosh Mariooryad and Carlos Busso. Correcting time-continuous emotional labels by modeling the reaction lag of evaluators. IEEE Transactions on Affective Computing, 6 (2): 97-108, April-June 2015.
14. Angeliki Metallinou, Athanasios Katsamanis, and Shrikanth Narayanan. Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech information. Image and Vision Computing, 31 (2): 137-152, February 2013.
15. Fabien Ringeval, Andreas Sonderegger, Jürgen Sauer, and Denis Lalanne. Introducing the RECOLA Multimodal Corpus of Remote Collaborative and Affective Interactions. In Proc. of EmoSPACE (held in conjunction with ACM FG), Shanghai, China, April 2013. 8 pages.
16. Fabien Ringeval, Florian Eyben, Eleni Kroupi, Anil Yuce, Jean-Philippe Thiran, Touradj Ebrahimi, Denis Lalanne, and Björn Schuller. Prediction of Asynchronous Dimensional Emotion Ratings from Audiovisual and Physiological Data. Pattern Recognition Letters, 66: 22-30, November 2015.
17. Fabien Ringeval, Björn Schuller, Michel Valstar, Shashank Jaiswal, Erik Marchi, Denis Lalanne, Roddy Cowie, and Maja Pantic. AV+EC 2015-The First Affect Recognition Challenge Bridging Across Audio, Video, and Physiological Data. In Proc. of AVEC (held in conjunction with ACM MM), pages 3-8, Brisbane, Australia, October 2015.
18. J. A. Russell. A circumplex model of affect. Journal of Personality and Social Psychology, 39 (6): 1161-1178, 1980.
19. Erik M. Schmidt and Youngmoo E. Kim. Modeling musical emotion dynamics with conditional random fields. In Proc. of ISMIR, pages 777-782, Miami, FL, USA, 2011.
20. Erik M. Schmidt, Jeffrey Scott, and Youngmoo E. Kim. Feature learning in dynamic environments: Modeling the acoustic structure of musical emotion. In Proc. of ISMIR, pages 325-330, Miami, FL, USA, 2012.
21. Björn Schuller, Michel Valstar, Florian Eyben, Roddy Cowie, and Maja Pantic. AVEC 2012-The Continuous Audio/Visual Emotion Challenge. In Louis-Philippe Morency, Dan Bohus, Hamid K. Aghajan, Justine Cassell, Anton Nijholt, and Julien Epps, editors, Proc. of ICMI, pages 449-456, Santa Monica, CA, October 2012. ACM.
22. Mohammad Soleymani, Michael N. Caro, Erik M. Schmidt, Chen-Ya Sha, and Yi-Hsuan Yang. 1000 songs for emotional analysis of music. In Proc. of CrowdMM (held in conjunction with ACM MM), Barcelona, Spain, 2013. ACM.
23. Karek Veselý, Arnab Ghoshal, Lukás Burget, and Daniel Povey. Sequence-discriminative training of deep neural networks. In Proc. of INTERSPEECH, pages 2345-2349, Lyon, France, 2013. ISCA.
24. Fengna Wang, Hichem Sahli, Junbin Gao, Dongmei Jiang, and Werner Verhelst. Relevance units machine based dimensional and continuous speech emotion prediction. Multimedia Tools and Applications, 74 (22): 9983-10000, November 2015.
25. Felix Weninger, Florian Eyben, and Björn Schuller. The TUM approach to the MediaEval music emotion task using generic affective audio features. In Martha Larson, Xavier Anguera, Timo Reuter, Gareth J. F. Jones, Bogdan Ionescu, Markus Schedl, Tomas Piatrik, Claudia Hauff, and Mohammad Soleymani, editors, Proc. of MediaEval, Barcelona, Spain, October 2013. CEUR.
26. Felix Weninger, John R. Hershey, Jonathan Le Roux, and Björn Schuller. Discriminatively trained recurrent neural networks for single-channel speech separation. In Proc. of GlobalSIP, pages 740-744, Atlanta, GA, USA, 2014. IEEE.
27. Felix Weninger, Johannes Bergmann, and Björn Schuller. Introducing CURRENNT-the Munich open-source CUDA RecurREnt Neural Network Toolkit. Journal of Machine Learning Research, 16: 547-551, 2015.