Augmenting Generative Adversarial Networks for Speech Emotion Recognition

TL;DR

This paper introduces a GAN-based framework augmented with mixup data augmentation to enhance speech emotion recognition by generating synthetic data and learning compressed emotional features, improving performance across datasets.

Contribution

It proposes a novel GAN augmentation framework using mixup for better feature learning and synthetic data generation in speech emotion recognition.

Findings

Effective learning of compressed emotional representations

Synthetic features improve within-corpus performance

Enhances cross-corpus speech emotion recognition

Abstract

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER) data. In this work, we propose a framework that utilises the mixup data augmentation scheme to augment the GAN in feature learning and generation. To show the effectiveness of the proposed framework, we present results for SER on (i) synthetic feature vectors, (ii) augmentation of the training data with synthetic features, (iii) encoded features in compressed representation. Our results show that the proposed framework can effectively learn compressed emotional representations as well as it can generate synthetic samples that help improve performance in within-corpus and cross-corpus evaluation.