# Endpoint Anticipation for Low-Latency Spoken Dialogue

arXiv: https://arxiv.org/abs/2606.13450 · HTML: https://mlsanity.com/paper/2606.13450/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2026.

## Built on by (most cited first, 2 of 2)

- [TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue](https://mlsanity.com/paper/2608.25218/) (2026)
- [Controlling Backchannels in Streamable Full-duplex Models](https://mlsanity.com/paper/2609.29418/) (2026)

## Abstract (arXiv)

While low-latency interaction is critical for spoken dialogue, cascaded architectures are often bottlenecked by reactive turn-completion detection. We propose Endpoint Anticipation, shifting from reactive detection to proactive forecasting of end-of-turn signals. Our speech-based model anticipates endpoints upto 2.56 seconds in advance, enabling speculative execution of LLM and TTS pipelines on partial context. We introduce metrics to quantify the trade-off between realized latency reduction and computational redundancy. Evaluation across conversational and task-oriented datasets shows our model consistently outperforms competitive VAP-based baselines. Integration with the Unmute framework demonstrates a 505 ms average latency reduction with a 28.4% increase in speculative computation, effectively masking sequential bottlenecks to enable complex reasoning in real-time speech-to-speech interaction.