EVALUATION OF TEMPORAL STABILITY OF EMOTIONS IN MULTIMODAL SIGNALS
Downloads
Keywords:
Multimodal emotion recognition, temporal stability, cross-modal attention, transformers, systematization of temporal consistency, Hurst exponent, autocorrelation, angular velocity (trajectory), conditional random fields (CRF), lack of modality robustnessAbstract
This paper proposes a methodological approach for evaluating the temporal stability of emotional states in multimodal data. Unlike previous studies, we introduce a multi-level formalization (signal → function → latent space → prediction) and a set of indicators including the number of class switches, episode duration, and the Hurst exponent. Stability is assessed at the level of trajectories in a polar space interpreted on the basis of Plutchik’s model. The study proposes a system of metrics describing temporal stability and provides a comparative analysis of these metrics across several multimodal architectures. The evaluation protocol includes speaker-independent splits, standard metrics (F1/UAR, CCC/MAE), and temporal stability indicators. As an additional validation step, a text-only pilot experiment was conducted on a balanced small subset of the MELD dataset. The proposed evaluation approach makes it possible to characterize the temporal stability properties of models more accurately. The practical value of the work lies in improving the predictability and interpretability of behavior in human-computer interaction systems and assistive technologies.
