提出无语音活动检测的全双工对话系统，实现快速双向交互。
DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
- 将长句转为微回合块处理，支持流式全双工交互。
- 在两个基准上达到开源系统最佳全双工表现。
- 适合需要自然流畅对话的智能语音助手场景。
基于级联ASR-LLM-TTS模块的语音对话系统虽保留了大语言模型的强大智能，但依赖语音活动检测（VAD）常导致半双工交互和控制脆弱。而无VAD的端到端模型虽支持全双工，却难以维持对话智能。本文提出DuplexCascade，一种无VAD的级联流式全双工语音对话系统。核心思想是将传统按句划分的长对话转为按块的微回合交互，实现在保持强大文本大模型能力的同时实现快速双向交流。为可靠协调发言权切换与响应时机，引入一组对话专用控制标记，引导大模型在流式约束下的行为。在Full-DuplexBench和VoiceBench基准上，DuplexCascade在开源语音对话系统中实现了顶尖的全双工对话能力与强对话智能。
原文摘要 · Abstract (English)
Spoken dialog systems with cascaded ASR-LLM-TTS modules retain strong LLM intelligence, but VAD segmentation often forces half-duplex turns and brittle control. On the other hand, VAD-free end-to-end model support full-duplex interaction but is hard to maintain conversational intelligence. In this paper, we present DuplexCascade, a VAD-free cascaded streaming pipeline for full-duplex speech-to-speech dialogue. Our key idea is to convert conventional utterance-wise long turns into chunk-wise micro-turn interactions, enabling rapid bidirectional exchange while preserving the strengths of a capable text LLM. To reliably coordinate turn-taking and response timing, we introduce a set of conversational special control tokens that steer the LLM's behavior under streaming constraints. On Full-DuplexBench and VoiceBench, DuplexCascade delivers state-of-the-art full-duplex turn-taking and strong conversational intelligence among open-source speech-to-speech dialogue systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。