# SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation

arXiv: https://arxiv.org/abs/2603.14877 · HTML: https://mlsanity.com/paper/2603.14877/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2026.

## Built on by (most cited first, 9 of 9)

- [Toward Native Multimodal Modeling: A Roadmap](https://mlsanity.com/paper/2605.25343/) (2026)
- [M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models](https://mlsanity.com/paper/2607.29125/) (2026)
- [X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction](https://mlsanity.com/paper/2608.10878/) (2026)
- [Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts](https://mlsanity.com/paper/2609.17360/) (2026)
- [Just A Rather Very Intelligent Spoken Agent](https://mlsanity.com/paper/2607.16610/) (2026)
- [JarvisBench: Always-on Intelligence Between Humans and Agents](https://mlsanity.com/paper/2608.14870/) (2026)
- [X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR](https://mlsanity.com/paper/2609.08672/) (2026)
- [FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex Speech](https://mlsanity.com/paper/2609.35791/) (2026)
- [XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions](https://mlsanity.com/paper/2610.04400/) (2026)

## Abstract (arXiv)

Recent advances in spoken dialogue systems have brought increased attention to human-like full-duplex voice interactions. However, our comprehensive review of this field reveals several challenges, including the difficulty in obtaining training data, catastrophic forgetting, and limited scalability. In this work, we propose SoulX-Duplug, a plug-and-play streaming state prediction module for full-duplex spoken dialogue systems. By jointly performing streaming ASR, SoulX-Duplug explicitly leverages textual information to identify user intent, effectively serving as a semantic VAD. To promote fair evaluation, we introduce SoulX-Duplug-Eval, extending widely used benchmarks with improved bilingual coverage. Experimental results show that SoulX-Duplug enables low-latency streaming dialogue state control, and the system built upon it outperforms existing full-duplex models in overall turn management and latency performance. We have open-sourced SoulX-Duplug and SoulX-Duplug-Eval.