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

arXiv: https://arxiv.org/abs/2609.13445 · HTML: https://mlsanity.com/paper/2609.13445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [Generalization in Generation: A closer look at Exposure Bias](https://mlsanity.com/paper/1910.00292/) (2019)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents](https://mlsanity.com/paper/2409.15594/) (2024)
- [PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models](https://mlsanity.com/paper/2602.06053/) (2026)
- [Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models](https://mlsanity.com/paper/2507.23159/) (2025)
- [A Full-duplex Speech Dialogue Scheme Based On Large Language Models](https://mlsanity.com/paper/2405.19487/) (2024)
- [Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing](https://mlsanity.com/paper/2410.17194/) (2024)
- [MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.12928/) (2026)
- [Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models](https://mlsanity.com/paper/2606.11167/) (2026)
- [DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization](https://mlsanity.com/paper/2603.09180/) (2026)

## Abstract (arXiv)

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 observed onset, speech probability spikes by over nine orders of magnitude in one 80-ms frame, supporting the latter hypothesis. Then, to suppress these onsets without blocking genuine responses, we ask a causal counterfactual question: is the model responding to user speech, or would its next-token distribution remain similar if the preceding user input were muted? Accordingly, we suppress onsets whose distributions change little under this intervention. Under realistic microphone noise, our method suppresses spurious onsets, while preserving genuine responses: one-sided 95% lower confidence bounds are 98.68% and 98.82% for Moshi, and 96.90% and 99.25% for PersonaPlex. Our inference-time method runs in real-time without retraining, with 95th-percentile decision time below 61 ms, within the 80-ms frame budget. Our code is available at https://github.com/KentoNishi/icassp27-spurious-onsets.