SOURCE-LINKED INTELLIGENCE

Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can begin speaking inappropriately during prolonged user silence: under digital-zero input, Moshi and PersonaPlex initiate speech in 30% and 27.5% of five-minute continuations, respectively. What causes this spurious speech? We investigate two hypotheses: either repeated sampling selects speech despite persistently low onset probabilities, or self-conditioning on nonspeech outputs causes an abrupt spike in onset probability. We find that, at every ob

Read original source ↗ Open in workspace

recordType

paper

region

Global