Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.
翻译:以集群为基础的发言者二分法是现实中的主要方法之一,尽管最近在端到端的二分法方面有所发展,但作为主要方法之一,分组法并没有为发言者二分法进行广泛探讨,但群集法没有为发言者二分法进行广泛探讨。通常使用的方法,如k手段、光谱群集和集聚性等级群集,只考虑近距离和相对密度等特性。在本文中,我们提议将基于集群的二分法视为一个社区检测问题。通过这样做,可以考虑地形结构。这项工作有四大贡献。首先,Leiden社区检测算法明显地优于先前关于发言者组集法的方法。第二,我们提议使用统一的多方向近似法来减少尺寸,同时保留全球和地方的地形结构。第三,采用遮掩过滤法来提取“干净”的发言者嵌入。最后,社区结构用于终端到终端的处理后网络,以获得二分解结果。最后系统显示将DER减少70%的相对比例。我们分析每个组成部分的分解。