Fine-grained Disentangled Representation Learning for Multimodal Emotion Recognition

TL;DR

This paper introduces a novel fine-grained disentangled representation learning framework for multimodal emotion recognition, effectively addressing heterogeneity and redundancy across modalities to improve recognition accuracy.

Contribution

The proposed FDRL framework uniquely separates shared and private modality representations with fine-grained alignment and disparity components for enhanced multimodal emotion recognition.

Findings

FDRL outperforms state-of-the-art methods on IEMOCAP dataset.

Achieves 78.34% WAR and 79.44% UAR, demonstrating superior accuracy.

Effectively captures modal consistency and diversity in representations.

Abstract

Multimodal emotion recognition (MMER) is an active research field that aims to accurately recognize human emotions by fusing multiple perceptual modalities. However, inherent heterogeneity across modalities introduces distribution gaps and information redundancy, posing significant challenges for MMER. In this paper, we propose a novel fine-grained disentangled representation learning (FDRL) framework to address these challenges. Specifically, we design modality-shared and modality-private encoders to project each modality into modality-shared and modality-private subspaces, respectively. In the shared subspace, we introduce a fine-grained alignment component to learn modality-shared representations, thus capturing modal consistency. Subsequently, we tailor a fine-grained disparity component to constrain the private subspaces, thereby learning modality-private representations and enhancing their diversity. Lastly, we introduce a fine-grained predictor component to ensure that the labels of the output representations from the encoders remain unchanged. Experimental results on the IEMOCAP dataset show that FDRL outperforms the state-of-the-art methods, achieving 78.34% and 79.44% on WAR and UAR, respectively.