Efficient Arabic Emotion Recognition Using Deep Neural Networks

• Published in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6710 - 6714
• Main Authors: Hifny, Yasser, Ali, Ahmed
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2019
• Subjects: and attention; bi-direction long short-term memory (BLSTM) networks; Computer architecture; convolutional neural networks (CNN); deep neural networks (DNN); Emotion recognition; Feature extraction; Speech emotion recognition; Speech recognition; Task analysis; Training
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2019.8683632

Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convo-lutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2% absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.