This paper introduces an online speaker diarization system that can handle long-time audio with low latency. We enable Agglomerative Hierarchy Clustering (AHC) to work in an online fashion by introducing a label matching algorithm. This algorithm solves the inconsistency between output labels and hidden labels that are generated each turn. To ensure the low latency in the online setting, we introduce a variant of AHC, namely chkpt-AHC, to cluster the speakers. In addition, we propose a speaker embedding graph to exploit a graph-based re-clustering method, further improving the performance. In the experiment, we evaluate our systems on both DIHARD3 and VoxConverse datasets. The experimental results show that our proposed online systems have better performance than our baseline online system and have comparable performance to our offline systems. We find out that the framework combining the chkpt-AHC method and the label matching algorithm works well in the online setting. Moreover, the chkpt-AHC method greatly reduces the time cost, while the graph-based re-clustering method helps improve the performance.
翻译:本文介绍一个可以处理长期低延迟音频的在线语音分解系统。 我们通过引入标签匹配算法, 使集压式等级分组(AHC)能够以在线方式工作。 这个算法可以解决输出标签和每转产生的隐藏标签之间的不一致性。 为了确保在线环境的低延迟性, 我们引入了一个AHC的变种, 即chkpt- AHC, 来分组演讲者。 此外, 我们提议用一个以图表为基础的重新分组方法嵌入一个发言者图, 以进一步改进性能。 在实验中, 我们评估了我们的 DISARD3 和 VoxConversion 数据集系统。 实验结果显示, 我们提议的在线系统比基线在线系统有更好的性能, 并且与我们的离线系统有类似的性能。 我们发现, 将 chkpt- AHC 方法和标签匹配算法结合的框架在在线环境中效果很好。 此外, chkpt- AHC 方法极大地降低了时间成本, 而基于图形的重新分组方法有助于改善业绩。