Enhancing Emotion Recognition in Incomplete Data: A Novel Cross-Modal Alignment, Reconstruction, and Refinement Framework

TL;DR

This paper introduces the CM-ARR framework, which improves multimodal emotion recognition when data from some modalities is missing by aligning, reconstructing, and refining representations using contrastive learning and normalizing flows.

Contribution

The novel CM-ARR framework combines cross-modal alignment, reconstruction with normalizing flows, and refinement to handle incomplete multimodal data for emotion recognition.

Findings

CM-ARR outperforms existing methods on IEMOCAP and MSP-IMPROV datasets.

Achieves over 2% improvements in WAR and UAR on average across missing modality scenarios.

Effective in both missing and complete modality conditions.

Abstract

Multimodal emotion recognition systems rely heavily on the full availability of modalities, suffering significant performance declines when modal data is incomplete. To tackle this issue, we present the Cross-Modal Alignment, Reconstruction, and Refinement (CM-ARR) framework, an innovative approach that sequentially engages in cross-modal alignment, reconstruction, and refinement phases to handle missing modalities and enhance emotion recognition. This framework utilizes unsupervised distribution-based contrastive learning to align heterogeneous modal distributions, reducing discrepancies and modeling semantic uncertainty effectively. The reconstruction phase applies normalizing flow models to transform these aligned distributions and recover missing modalities. The refinement phase employs supervised point-based contrastive learning to disrupt semantic correlations and accentuate emotional traits, thereby enriching the affective content of the reconstructed representations. Extensive experiments on the IEMOCAP and MSP-IMPROV datasets confirm the superior performance of CM-ARR under conditions of both missing and complete modalities. Notably, averaged across six scenarios of missing modalities, CM-ARR achieves absolute improvements of 2.11% in WAR and 2.12% in UAR on the IEMOCAP dataset, and 1.71% and 1.96% in WAR and UAR, respectively, on the MSP-IMPROV dataset.