Multimodal emotion recognition (MER) in practical scenarios presents a significant challenge due to the presence of incomplete data, such as missing or noisy data. Traditional methods often discard missing data or replace it with a zero vector, neglecting the availability issue of noisy data. Consequently, these approaches are not fully applicable to realistic scenarios, where both missing and noisy data are prevalent. To address this problem, we propose a novel noise-robust MER model, named NMER, which effectively learns robust multimodal joint representations from incomplete data containing noise. Our approach incorporates two key components. First, we introduce a noise scheduler that adjusts the type and level of noise in the training data, emulating the characteristics of incomplete data in realistic scenarios. Second, we employ a Variational AutoEncoder (VAE)-based NMER model to generate robust multimodal joint representations from the noisy data, leveraging the modality invariant feature. The experimental results on the benchmark dataset IEMOCAP indicate the proposed NMER outperforms state-of-the-art MER systems. The ablation results also confirm the effectiveness of the VAE structure. We release our code at \href{https://github.com/WooyoohL/Noise-robust_MER.

Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing data across modalities, the inherent difference between heterogeneous modalities, namely the modality gap, presents a challenge. To address this, we propose to use invariant features for a missing modality imagination network (IF-MMIN) which includes two novel mechanisms: 1) an invariant feature learning strategy that is based on the central moment discrepancy (CMD) distance under the full-modality scenario; 2) an invariant feature based imagination module (IF-IM) to alleviate the modality gap during the missing modalities prediction, thus improving the robustness of multimodal joint representation. Comprehensive experiments on the benchmark dataset IEMOCAP demonstrate that the proposed model outperforms all baselines and invariantly improves the overall emotion recognition performance under uncertain missing-modality conditions. We release the code at: https://github.com/ZhuoYulang/IF-MMIN.