Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives

Abstract

Over the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains. As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective computing and sentiment analysis. Various representative adversarial training algorithms are explained and discussed accordingly, aimed at tackling diverse challenges associated with emotional AI systems. Further, we highlight a range of potential future research directions. We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.

References in corpus (39)

• Conditional Generative Adversarial Nets
• Generative Adversarial Networks: An Overview
• WaveNet: A Generative Model for Raw Audio
• Conditional Image Generation with PixelCNN Decoders
• Pixel Recurrent Neural Networks
• Improved Techniques for Training GANs
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Energy-based Generative Adversarial Network
• End-to-End Multimodal Emotion Recognition using Deep Neural Networks
• Adversarial Feature Learning
• Semi-Supervised Learning with Generative Adversarial Networks
• Unrolled Generative Adversarial Networks
• C-RNN-GAN: Continuous recurrent neural networks with adversarial training
• Distributional Smoothing with Virtual Adversarial Training
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Mode Regularized Generative Adversarial Networks
• Triple Generative Adversarial Nets
• Adversarial Learning for Neural Dialogue Generation
• Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks
• Domain Adversarial for Acoustic Emotion Recognition
• Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
• AdaGAN: Boosting Generative Models
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Adversarial Generation of Natural Language
• ExprGAN: Facial Expression Editing with Controllable Expression Intensity
• Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
• Emotional End-to-End Neural Speech Synthesizer
• Geometry-Contrastive GAN for Facial Expression Transfer
• Towards Open-Set Identity Preserving Face Synthesis
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
• Talking Face Generation by Conditional Recurrent Adversarial Network
• ArtGAN: Artwork Synthesis with Conditional Categorical GANs
• Geometry Guided Adversarial Facial Expression Synthesis
• Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
• Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions
• Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
• Correlated discrete data generation using adversarial training
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets

Cited by in corpus (7)

• Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Adversarial-based neural networks for affect estimations in the wild
• Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing
• It's LeVAsa not LevioSA! Latent Encodings for Valence-Arousal Structure Alignment
• Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention