Streaming Sortformer：基于说话人缓存且按到达时间排序的在线说话人日志分离
Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering
AI总结：
本文为 Sortformer 提出流式扩展，利用按到达时间排序并动态更新的 AOSC 缓存帧级嵌入，实现低延迟、高精度的实时在线多说话人日志分离。
摘要：
本文提出了 Sortformer 说话人日志分离框架的一种流式扩展，其关键特性是输出说话人按到达时间排序。所提方法采用到达顺序说话人缓存（Arrival-Order Speaker Cache，AOSC）来存储先前已观测说话人的帧级声学嵌入。与传统的说话人追踪缓冲区不同，AOSC 按照与说话人到达时间顺序相对应的说话人索引对嵌入进行排序，并通过依据模型过去的预测选择得分最高的帧来进行动态更新。值得注意的是，每位说话人存储的嵌入数量由更新机制动态决定，从而确保高效的缓存利用和精确的说话人追踪。在多个基准数据集上的实验证实了该方法的有效性和灵活性，即使在低延迟设置下也是如此。这些结果确立了 Streaming Sortformer 作为实时多说话人追踪的稳健解决方案，并为流式多说话者语音处理奠定了基础。
英文摘要：
This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approach employs an Arrival-Order Speaker Cache (AOSC) to store frame-level acoustic embeddings of previously observed speakers. Unlike conventional speaker-tracing buffers, AOSC orders embeddings by speaker index corresponding to their arrival time order, and is dynamically updated by selecting frames with the highest scores based on the model's past predictions. Notably, the number of stored embeddings per speaker is determined dynamically by the update mechanism, ensuring efficient cache utilization and precise speaker tracking. Experiments on benchmark datasets confirm the effectiveness and flexibility of our approach, even in low-latency setups. These results establish Streaming Sortformer as a robust solution for real-time multi-speaker tracking and a foundation for streaming multi-talker speech processing.
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。
