基于单元的代理用于半级联全双工对话系统
Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems
AI总结：
本文提出基于单元的半级联全双工对话系统，利用多模态大语言模型和辅助模块实现高效对话处理，实验显示其在挑战赛中表现优异。
摘要：
全双工语音交互对于自然人机交互至关重要。我们提出了一种框架，将复杂的对话分解为最小的会话单元，使系统能够独立处理每个单元并预测何时过渡到下一个阶段。该框架被实例化为一个围绕多模态大语言模型构建的半级联全双工对话系统，辅以语音活动检测（VAD）和文本到语音（TTS）合成等辅助模块。所得到的系统以无需训练的即插即用方式运行。在HumDial数据集上的实验表明，我们的框架在人类样语音对话系统挑战（Track 2：全双工交互）的测试集上排名第二。代码可在GitHub仓库https://github.com/yu-haoyuan/fd-badcat上获得。
英文摘要：
Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal conversational units, enabling the system to process each unit independently and predict when to transit to the next. This framework is instantiated as a semi-cascaded full-duplex dialogue system built around a multimodal large language model, supported by auxiliary modules such as voice activity detection (VAD) and text-to-speech (TTS) synthesis. The resulting system operates in a train-free, plug-and-play manner. Experiments on the HumDial dataset demonstrate the effectiveness of our framework, which ranks second among all teams on the test set of the Human-like Spoken Dialogue Systems Challenge (Track 2: Full-Duplex Interaction). Code is available at the GitHub repository https://github.com/yu-haoyuan/fd-badcat.
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。
