A Review of Human Emotion Synthesis Based on Generative Technology

TL;DR

This paper systematically reviews recent advances in human emotion synthesis using generative models, covering methodologies, datasets, modalities, and evaluation metrics to provide a comprehensive overview of the field.

Contribution

It offers the first thorough review of generative technology applications in emotion synthesis, highlighting recent progress and future research directions.

Findings

Generative models significantly improve emotion synthesis quality.

Multimodal approaches enhance naturalness in emotion expression.

Evaluation metrics vary across modalities and models.

Abstract

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interactions. Recent advancements in generative models, such as Autoencoders, Generative Adversarial Networks, Diffusion Models, Large Language Models, and Sequence-to-Sequence Models, have significantly contributed to the development of this field. However, there is a notable lack of comprehensive reviews in this field. To address this problem, this paper aims to address this gap by providing a thorough and systematic overview of recent advancements in human emotion synthesis based on generative models. Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used. Then, the review covers the application of different generative models to emotion synthesis based on a variety of modalities, including facial images, speech, and text. It also examines mainstream evaluation metrics. Additionally, the review presents some major findings and suggests future research directions, providing a comprehensive understanding of the role of generative technology in the nuanced domain of emotion synthesis.