Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems

TL;DR

This paper introduces DDTSR, a low-latency streaming framework for spoken dialogue systems that enables simultaneous listening, reasoning, and speaking, significantly reducing response time while maintaining discourse quality.

Contribution

The paper presents a novel discourse-aware dual-track streaming architecture that enables real-time, low-latency responses in spoken dialogue systems through innovative model synergy and streaming collaboration.

Findings

Reduces response latency by up to 51%

Maintains discourse coherence and quality

Compatible with diverse LLM backbones

Abstract

Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning before speech synthesis can begin, which results in high response latency. We propose the Discourse-Aware Dual-Track Streaming Response (DDTSR) framework, a low-latency architecture that enables listen-while-thinking and speak-while-thinking. DDTSR is built upon three key mechanisms: (1) connective-guided small-large model synergy, where an auxiliary small model generates minimal-committal discourse connectives while a large model performs knowledge-intensive reasoning in parallel; (2) streaming-based cross-modal collaboration, which dynamically overlaps ASR, LLM inference, and TTS to advance the earliest speakable moment; and (3) curriculum-learning-based discourse continuity enhancement, which maintains coherence and logical consistency between early responses and subsequent reasoning outputs. Experiments on two spoken dialogue benchmarks demonstrate that DDTSR reduces response latency by 19%-51% while preserving discourse quality. Further analysis shows that DDTSR functions as a plug-and-play module compatible with diverse LLM backbones, and remains robust across varying utterance lengths, indicating strong practicality and scalability for real-time spoken interaction.