On Enhancing Speech Emotion Recognition Using Generative Adversarial Networks

Abstract

Generative Adversarial Networks (GANs) have gained a lot of attention from machine learning community due to their ability to learn and mimic an input data distribution. GANs consist of a discriminator and a generator working in tandem playing a min-max game to learn a target underlying data distribution; when fed with data-points sampled from a simpler distribution (like uniform or Gaussian distribution). Once trained, they allow synthetic generation of examples sampled from the target distribution. We investigate the application of GANs to generate synthetic feature vectors used for speech emotion recognition. Specifically, we investigate two set ups: (i) a vanilla GAN that learns the distribution of a lower dimensional representation of the actual higher dimensional feature vector and, (ii) a conditional GAN that learns the distribution of the higher dimensional feature vectors conditioned on the labels or the emotional class to which it belongs. As a potential practical application

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keysahu2018on

Related papers

• Modeling Feature Representations For Affective Speech Using Generative Adversarial Networks (2019)0.00
• Augmenting Generative Adversarial Networks For Speech Emotion Recognition (2020)10.85
• Adversarial Auto-encoders For Speech Based Emotion Recognition (2018)12.68
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• Improving Speech Emotion Recognition With Mutual Information Regularized Generative Model (2025)0.00
• Emotion Detection Using Conditional Generative Adversarial Networks (cgan): A Deep Learning Approach (2025)0.00
• Learning Representations Of Emotional Speech With Deep Convolutional Generative Adversarial Networks (2017)0.00
• Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness (2018)0.00