Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
Duplex Cue evaluation shows PersonaPlex full-duplex agents adapt in-turn to listener contributions in only 34.8% of collaborative cases versus 68.2% for humans.
The paper introduces Duplex Cue, an evaluation of in-turn adaptation in full-duplex voice agents that separates listener intent (backchannel, collaboration, interruption) from speaker behavior (continue, adapt, yield). Using 208 scorable pairs from 300 human-confirmed cues in unscripted English conversations, it compares recorded human responses with PersonaPlex continuations generated while replaying listener audio. Humans adapt within the turn in 68.2% of collaborative pairs versus 34.8% for PersonaPlex, which otherwise continues unchanged (42.4%) or yields (22.7%).
- Evaluates in-turn adaptation, not just speak-or-stop behavior
- Separates listener intent taxonomy from speaker response behavior
- Humans adapt in 68.2% of collaborative cues; PersonaPlex only 34.8%
- Built on 300 human-confirmed cues from unscripted conversations
From the original article
1 min read at arxiv.orgFull-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: continuing to speak while incorporating what the listener just contributed. The contribution may be a missing word, a correction or a clarification.
By Yunqi Lu · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.