LTS-VoiceAgent: 一种基于语义触发和增量推理的高效语音交互流式框架
LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning
AI总结：
LTS-VoiceAgent通过语义触发和增量推理实现高效语音交互，提升流式处理的准确性和效率。
摘要：
实时语音代理面临一个两难问题：端到端模型往往缺乏深度推理能力，而级联流水线则因依次执行语音识别、大语言模型推理和文本到语音转换而产生高延迟，这与人类对话中听众常在说话人完成之前就开始思考的情况不同。由于级联架构仍然是复杂任务的主导选择，现有的级联流式策略试图通过机械分割（例如固定块、基于VAD的分割）或推测生成来减少这种延迟，但它们经常要么破坏语义单元，要么浪费计算资源在必须回滚的预测上。为了解决这些挑战，我们提出了LTS-VoiceAgent，一种Listen-Think-Speak框架，它明确区分何时思考和如何进行增量推理。该框架具有动态语义触发器，用于检测有意义的前缀，以及一个双角色流协调器，协调一个后台思考者（用于状态维护）和一个前台说话者（用于推测解决）。这种并行设计使“思考的同时说话”成为可能，而不会阻塞响应。我们还引入了一个Pause-and-Repair基准，包含自然的不流畅性，以压力测试流式鲁棒性。实验结果表明，LTS-VoiceAgent在VERA、Spoken-MQA、BigBenchAudio和我们基准测试中均实现了比串行级联基线和现有流式策略更优的准确性-延迟-效率权衡。
英文摘要：
Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often start thinking before the speaker finishes. Since cascaded architectures remain the dominant choice for complex tasks, existing cascaded streaming strategies attempt to reduce this latency via mechanical segmentation (e.g., fixed chunks, VAD-based splitting) or speculative generation, but they frequently either break semantic units or waste computation on predictions that must be rolled back. To address these challenges, we propose LTS-VoiceAgent, a Listen-Think-Speak framework that explicitly separates when to think from how to reason incrementally. It features a Dynamic Semantic Trigger to detect meaningful prefixes, and a Dual-Role Stream Orchestrator that coordinates a background Thinker (for state maintenance) and a foreground Speaker (for speculative solving). This parallel design enables "thinking while speaking" without blocking responses. We also introduce a Pause-and-Repair benchmark containing natural disfluencies to stress-test streaming robustness. Experiments across VERA, Spoken-MQA, BigBenchAudio, and our benchmark show that LTS-VoiceAgent achieves a stronger accuracy-latency-efficiency trade-off than serial cascaded baselines and existing streaming strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
