# FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex Speech

arXiv: https://arxiv.org/abs/2609.35791 · HTML: https://mlsanity.com/paper/2609.35791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training](https://mlsanity.com/paper/2412.15649/) (2024)
- [Easy Turn: Integrating Acoustic and Linguistic Modalities for Robust Turn-Taking in Full-Duplex Spoken Dialogue Systems](https://mlsanity.com/paper/2509.23938/) (2025)
- [SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation](https://mlsanity.com/paper/2603.14877/) (2026)
- [TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue](https://mlsanity.com/paper/2608.25218/) (2026)
- [Speculative End-Turn Detector for Efficient Speech Chatbot Assistant](https://mlsanity.com/paper/2503.23439/) (2025)
- [FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection](https://mlsanity.com/paper/2604.01897/) (2026)
- [X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction](https://mlsanity.com/paper/2608.10878/) (2026)
- [Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction](https://mlsanity.com/paper/2606.18094/) (2026)
- [TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection](https://mlsanity.com/paper/2609.04240/) (2026)

## Abstract (arXiv)

Natural turn-taking in full-duplex voice interaction requires determining from partial speech whether a pause reflects hesitation or a completed conversational intent. Acoustic voice activity detection lacks this semantic information, while cascaded ASR-based endpointing introduces transcription dependence and additional processing stages. We formulate semantic endpoint detection as a causal audio-language reasoning task and introduce FD-VAD, an ASR-free streaming endpointer that maps bounded causal audio windows directly to Continue/Stop decisions. FD-VAD combines a frozen speech encoder with a lightweight modality adapter and a parameter-efficiently adapted language model, using a last-chunk training objective for streaming inference. We further introduce confidence-gated endpoint commitment to control interruption versus delay and boundary-focused hard-negative sampling to improve decisions around ambiguous turn boundaries. Across in-domain and conversational evaluations, FD-VAD outperforms strong streaming and non-streaming semantic turn classifiers, and achieves the highest EOT recall among qualifying systems on TurnBench dev set 0.853 (at FP<=0.10) in a zero-shot setting. These results show that semantic endpointing can be performed directly from streaming audio without intermediate ASR or dialogue state tracking.