Apr 26, 2022 · In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered.

First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we ...

Here we develop a method that incorporates both the topology of interactions and node attributes to extract communities in multilayer networks. We propose a ...

UMAP-Leiden: "Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure", in Proc. ICASSP, 2022. (Alibaba) [Paper] ...

2204.12112 - Free download as PDF File (.pdf), Text File (.txt) or read online for free.

Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure ... In this paper we propose to view clustering-based diarization ...

Jul 25, 2024 · Reformulating Speaker Diarization As Community Detection With Emphasis On Topological Structure. ICASSP 2022: 8097-8101. [c16]. view.

Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization.

In this paper we describe a speaker diarization system that enables localization and identification of all speakers present in a conversation or meeting.

Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure. Clustering-based speaker diarization has stood firm as one ...