# Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

arXiv: https://arxiv.org/abs/2607.23204 · HTML: https://mlsanity.com/paper/2607.23204/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 25 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models](https://mlsanity.com/paper/2602.06053/) (2026)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://mlsanity.com/paper/2010.10874/) (2020)
- [Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection](https://mlsanity.com/paper/2401.04868/) (2024)
- [Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs](https://mlsanity.com/paper/1806.11461/) (2018)
- [Applying General Turn-taking Models to Conversational Human-Robot Interaction](https://mlsanity.com/paper/2501.08946/) (2025)
- [Mitigating Response Delays in Free-Form Conversations with LLM-powered Intelligent Virtual Agents](https://mlsanity.com/paper/2507.22352/) (2025)
- [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)
- [A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment](https://mlsanity.com/paper/2503.06241/) (2025)

## Abstract (arXiv)

Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Once user intent becomes predictable, an intent readiness detector triggers LLM-based generation of a short prefatory response. Concurrently, a voice activity projection (VAP) model determines when to deliver it. Through a field experiment with a route-guidance robot in a shopping mall, we evaluated three conditions: no-filler, fixed-filler, and contextual-preface. Both fixed-filler and contextual-preface significantly reduced initial response latency relative to no-filler. Relative to fixed-filler, contextual-preface had significantly longer initial response latency but a significantly shorter initial-to-main gap. Exploratory ratings showed no significant differences. These results indicate a timing trade-off.