Efficient Arabic emotion recognition using deep neural networks

TL;DR

This paper introduces two deep neural network architectures for Arabic speech emotion recognition, demonstrating improved accuracy with the CNN-LSTM-DNN model and faster training with the deep CNN model.

Contribution

It presents a novel attention-based CNN-LSTM-DNN architecture and compares its performance with a deep CNN, advancing Arabic emotion recognition techniques.

Findings

CNN-LSTM-DNN achieves 2.2% higher accuracy than baseline

Deep CNN models train faster than CNN-LSTM-DNN

Both models outperform previous approaches in accuracy

Abstract

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 convolutional 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.