Towards real-time Speech Emotion Recognition using deep neural networks
Authors:
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Most existing Speech Emotion Recognition (SER) systems rely on turn-wise processing, which aims at recognizing emotions from complete utterances and an overly-complicated pipeline marred by many preprocessing steps and hand-engineered features. To overcome both drawbacks, we propose a real-time SER system based on end-to-end deep learning. Namely, a Deep Neural Network (DNN) that recognizes emotions from a one second frame of raw speech spectrograms is presented and investigated. This is achievable due to a deep hierarchical architecture, data augmentation, and sensible regularization. Promising results are reported on two databases which are the eNTERFACE database and the Surrey Audio-Visual Expressed Emotion (SAVEE) database.Keywords
This publication has 14 references indexed in Scilit:
- Deep learningNature, 2015
- Optimized multi-channel deep neural network with 2D graphical representation of acoustic speech features for emotion recognition2014
- A tutorial survey of architectures, algorithms, and applications for deep learningAPSIPA Transactions on Signal and Information Processing, 2014
- Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition2013
- On rectified linear units for speech processing2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Acoustic Modeling Using Deep Belief NetworksIEEE Transactions on Audio, Speech, and Language Processing, 2011
- On-line emotion recognition in a 3-D activation-valence-time continuum using acoustic and linguistic cuesJournal on Multimodal User Interfaces, 2009
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- The eNTERFACE’05 Audio-Visual Emotion Database2006