Representation Learning with Graph Neural Networks for Speech Emotion Recognition

TL;DR

This paper introduces CoGCN, a graph neural network model using cosine similarity for speech emotion recognition, demonstrating robustness to noise and superior performance with fewer parameters.

Contribution

The paper proposes a novel cosine similarity-based graph structure and CoGCN model for SER, improving noise robustness and reducing model size compared to existing methods.

Findings

Outperforms state-of-the-art SER methods

Achieves significant model size reduction

Demonstrates robustness to speech noise

Abstract

Learning expressive representation is crucial in deep learning. In speech emotion recognition (SER), vacuum regions or noises in the speech interfere with expressive representation learning. However, traditional RNN-based models are susceptible to such noise. Recently, Graph Neural Network (GNN) has demonstrated its effectiveness for representation learning, and we adopt this framework for SER. In particular, we propose a cosine similarity-based graph as an ideal graph structure for representation learning in SER. We present a Cosine similarity-based Graph Convolutional Network (CoGCN) that is robust to perturbation and noise. Experimental results show that our method outperforms state-of-the-art methods or provides competitive results with a significant model size reduction with only 1/30 parameters.