TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
This work provides a new dataset and method for detecting emotional entrainment in dyadic speech, which is relevant for speech AI agents, but the problem is domain-specific and the dataset is synthetic.
The authors introduce DyadEE, a dataset for emotional entrainment detection in dyadic speech, and propose TRACE, a window-level framework that models interaction traces. TRACE achieves 97.01% accuracy on DyadEE.
With the proliferation of speech AI agents, understanding emotional entrainment in conversational interaction has become increasingly important. Emotional entrainment is shaped by social relationships and conversational context, influencing affective coordination over time. We introduce DyadEE, a dataset for emotional entrainment detection in dyadic speech interactions, containing both emotionally entrained conversations and synthetic interactions where entrainment is disrupted through partner swapping and emotion resynthesis. We further propose TRACE, a window-level framework that models dyadic interaction as ordered sequences of acoustic embeddings derived from emotion fine-tuned Whisper representations, treating each sample as an interaction trace rather than pooled utterances. Experimental results on DyadEE show that incorporating conversational context and relationship information improves emotional entrainment detection, with TRACE achieving the best accuracy of 97.01%.