Acted vs. Improvised: Domain Adaptation for Elicitation Approaches in Audio-Visual Emotion Recognition

TL;DR

This paper investigates domain adaptation techniques to improve audio-visual emotion recognition across different elicitation approaches, addressing data scarcity and variability in emotional expressions.

Contribution

It introduces a novel domain transfer learning method combining gradient reversal, entropy loss, and softlabel loss for emotion recognition across elicitation contexts.

Findings

Domain transfer learning reduces mismatch between acted and improvised emotion data.

The proposed method improves recognition accuracy with limited labeled data.

Insights into how elicitation strategies impact emotion data collection.

Abstract

Key challenges in developing generalized automatic emotion recognition systems include scarcity of labeled data and lack of gold-standard references. Even for the cues that are labeled as the same emotion category, the variability of associated expressions can be high depending on the elicitation context e.g., emotion elicited during improvised conversations vs. acted sessions with predefined scripts. In this work, we regard the emotion elicitation approach as domain knowledge, and explore domain transfer learning techniques on emotional utterances collected under different emotion elicitation approaches, particularly with limited labeled target samples. Our emotion recognition model combines the gradient reversal technique with an entropy loss function as well as the softlabel loss, and the experiment results show that domain transfer learning methods can be employed to alleviate the domain mismatch between different elicitation approaches. Our work provides new insights into emotion data collection, particularly the impact of its elicitation strategies, and the importance of domain adaptation in emotion recognition aiming for generalized systems.