Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm

2025-06-03 · Zhaoyang Li, Jie Wang, Xiaoxiao Li, Wangjie Li, Longjie Luo, Lin Li, Qingyang Hong

In speaker diarization, traditional clustering-based methods remain widely used in real-world applications. However, these methods struggle with the complex distribution of speaker embeddings and overlapping speech segments. To address these limitations, we propose an Overlapping Community Detection method based on Graph Attention networks and the Label Propagation Algorithm (OCDGALP). The proposed framework comprises two key components: (1) a graph attention network that refines speaker embeddings and node connections by aggregating information from neighboring nodes, and (2) a label propagation algorithm that assigns multiple community labels to each node, enabling simultaneous clustering and overlapping community detection. Experimental results show that the proposed method significantly reduces the Diarization Error Rate (DER), achieving a state-of-the-art 15.94% DER on the DIHARD-III dataset without oracle Voice Activity Detection (VAD), and an impressive 11.07% with oracle VAD.

📄 PDF Abstract BibTeX arXiv:2506.02610

Code (1)

yurakuratov/hidden_capacity pytorch

Tasks

Action Detection Activity DetectionClusteringCommunity DetectionGraph Attentionspeaker-diarization Speaker Diarization

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization

2023-06-26 · Jie Wang, Zhicong Chen, Haodong Zhou, Lin Li 외

The clustering algorithm plays a crucial role in speaker diarization systems. However, traditional clustering algorithms suffer from the complex distribution of speaker embeddings and lack of digging potential relationsh…

Clustering Community Detection Graph Generation speaker-diarization+1

End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection

2021-06-08 · Yuki Takashima, Yusuke Fujita, Shinji Watanabe, Shota Horiguchi 외

In this paper, we present a conditional multitask learning method for end-to-end neural speaker diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, espe…

Clustering speaker-diarization Speaker Diarization

Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios

2024-01-08 · Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla 외

We propose a modified teacher-student training for the extraction of frame-wise speaker embeddings that allows for an effective diarization of meeting scenarios containing partially overlapping speech. To this end, a geo…

Clustering

Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure

2022-04-26 · Siqi Zheng, Hongbin Suo

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 spea…

Clustering Community Detection speaker-diarization Speaker Diarization

Using Active Speaker Faces for Diarization in TV shows

2022-03-30 · Rahul Sharma, Shrikanth Narayanan

Speaker diarization is one of the critical components of computational media intelligence as it enables a character-level analysis of story portrayals and media content understanding. Automated audio-based speaker diariz…

Face Clustering Face Detection speaker-diarization Speaker Diarization