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

TL;DR

SoulX-Duplug is a plug-and-play streaming module for full-duplex speech systems that improves dialogue state prediction and latency, leveraging textual info for better intent recognition and semantic VAD.

Contribution

It introduces a novel streaming state prediction module that is plug-and-play, explicitly uses textual information for intent detection, and extends evaluation benchmarks for better assessment.

Findings

Outperforms existing models in turn management

Enables low-latency dialogue control

Improves bilingual coverage in evaluation benchmarks

Abstract

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.