TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Sathvik Manikantan Napa Ugandhar, Hao Zhang, Alison Gunzler, Yuzhe Wang, Thomas Thebaud, Georgi Tinchev, Venkatesh Ravichandran, Laureano Moro-Velázquez
• Venue: arXiv: cs.CL
• Published: 2026-06-29
• Collected: 2026-06-30
• URL: http://arxiv.org/abs/2606.30543v1
• PDF: https://arxiv.org/pdf/2606.30543v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers have introduced a new dataset called DyadEE for studying emotional entrainment in two-person conversations. They also developed a model called TRACE that uses acoustic embeddings from emotion-fine-tuned Whisper representations to analyze conversational interactions as 'interaction traces'. The results show that incorporating conversational context and relationship information improves emotional entrainment detection, with TRACE achieving an accuracy of 97.01%.

What the Document Says

• The study introduces DyadEE, a dataset for analyzing emotional entrainment in two-person conversations.
• DyadEE contains both emotionally entrained conversations and synthetic interactions where entrainment is disrupted.
• TRACE is a model that uses acoustic embeddings from emotion-fine-tuned Whisper representations to analyze conversational interactions.
• Each sample in TRACE is treated as an 'interaction trace' rather than pooled utterances.
• Experimental results on DyadEE show that incorporating conversational context and relationship information improves emotional entrainment detection.
• TRACE achieved the best accuracy of 97.01%.

Key Concepts Mentioned

• emotional entrainment
• dyadic speech interactions
• DyadEE dataset
• TRACE model
• acoustic embeddings
• Whisper representations

Claims Made by the Document

• Incorporating conversational context and relationship information improves emotional entrainment detection.
• TRACE achieved the best accuracy of 97.01%.

Evidence Used

• 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%.

Methods / Approach

• Using a dataset called DyadEE for emotional entrainment detection.
• Developing a model called TRACE that uses acoustic embeddings from emotion-fine-tuned Whisper representations

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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%.