研究人员开发了新的方法来增强全双工语音模型，从而实现更自然、更具交互性的对话。一种方法侧重于使用强化学习来改进暂停处理和轮流发言等交互轴，并将其应用于 Moshi 和 PersonaPlex 等模型。另一种方法，Listen-Write-Speak (LWS)，引入了一种以文本为中心的范式，模型可以同时收听、写入可见文本并进行语音输出，利用文本原生能力而不牺牲实时响应能力。 AI
影响 这些进步可能带来更自然、更强大的语音助手和对话式AI系统。
排序理由 该集群包含两篇研究论文，详细介绍了全双工语音模型的新方法。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2606.11386v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplore…
arXiv:2606.11167v1 Announce Type: new Abstract: Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, current models are trained solely with supervised learning through token-level likelihoo…
Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, current models are trained solely with supervised learning through token-level likelihood maximization, which does not directly optimize…
arXiv:2606.07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis,…
A text-first tri-channel speech interface enables real-time interaction with visible text output alongside spoken responses, demonstrating superior performance in full-duplex conversational tasks.