EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation

TL;DR

EmoSpeaker is a novel method for fine-grained emotion-controlled talking face generation that improves emotional expression and lip synchronization using a visual attribute-guided audio decoupler and emotion intensity control.

Contribution

The paper introduces a visual attribute-guided audio decoupler, a fine-grained emotion coefficient prediction module, and an emotion intensity control method, advancing emotion control in talking face generation.

Findings

Outperforms existing methods in expression variation

Enhances lip synchronization accuracy

Enables finer emotion intensity classification

Abstract

Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional states, thereby improving the emotional quality and personalization of generated content. Generating fine-grained facial animations that accurately portray emotional expressions using only a portrait and an audio recording presents a challenge. In order to address this challenge, we propose a visual attribute-guided audio decoupler. This enables the obtention of content vectors solely related to the audio content, enhancing the stability of subsequent lip movement coefficient predictions. To achieve more precise emotional expression, we introduce a fine-grained emotion coefficient prediction module. Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix. Through these, effective control over emotional expression in the generated videos and finer classification of emotion intensity are accomplished. Subsequently, a series of 3DMM coefficient generation networks are designed to predict 3D coefficients, followed by the utilization of a rendering network to generate the final video. Our experimental results demonstrate that our proposed method, EmoSpeaker, outperforms existing emotional talking face generation methods in terms of expression variation and lip synchronization. Project page: https://peterfanfan.github.io/EmoSpeaker/