绝对的决定绝对腐败：保守的在线发言人日记
Absolute decision corrupts absolutely: conservative online speaker diarisation
摘要：
我们的重点在于开发一个在线演讲者diarisation框架，该框架在不同的领域表现出强大的性能。在在线演讲者日记中，实时生成的输出是不可逆的，并且在输入会话的早期阶段的一些误判可能导致灾难性的结果。我们假设，谨慎地增加估计扬声器的数量是至关重要的许多其他因素。因此，我们提出的框架包括当系统判断过去增加发言者人数是错误的时，减少一名发言者。我们还采用了双缓冲区，检查点和质心，其中检查点与轮廓系数相结合，以估计说话人的数量和质心代表说话人。同样，我们认为，可以从一个扬声器产生一个以上的质心。因此，我们设计了一个基于聚类的标签匹配技术，实时分配标签。由此产生的系统是轻量级的，但令人惊讶的有效。该系统在DIHARD 2和3数据集上展示了最先进的性能，在AMI和VoxConverse测试集上也具有竞争力。
英文摘要：
Our focus lies in developing an online speaker diarisation framework which demonstrates robust performance across diverse domains. In online speaker diarisation, outputs generated in real-time are irreversible, and a few misjudgements in the early phase of an input session can lead to catastrophic results. We hypothesise that cautiously increasing the number of estimated speakers is of paramount importance among many other factors. Thus, our proposed framework includes decreasing the number of speakers by one when the system judges that an increase in the past was faulty. We also adopt dual buffers, checkpoints and centroids, where checkpoints are combined with silhouette coefficients to estimate the number of speakers and centroids represent speakers. Again, we believe that more than one centroid can be generated from one speaker. Thus we design a clustering-based label matching technique to assign labels in real-time. The resulting system is lightweight yet surprisingly effective. The system demonstrates state-of-the-art performance on DIHARD 2 and 3 datasets, where it is also competitive in AMI and VoxConverse test sets.
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。
