用图注意力网络和标签传播实现重叠语音的说话人聚类，性能领先
Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm
- 构建图注意力网络优化说话人嵌入与连接关系
- 通过标签传播实现单节点多身份识别，支持重叠段落检测
- 在DIHARD-III数据集上达11.07%低错误率，适合复杂对话场景
在说话人分离任务中，传统聚类方法仍广泛应用于实际场景，但难以处理说话人嵌入分布复杂及重叠语音段的问题。为此，本文提出基于图注意力网络与标签传播算法的重叠社区检测方法（OCDGALP）。该框架包含两个核心组件：(1) 图注意力网络通过聚合邻近节点信息，优化说话人嵌入与节点连接；(2) 标签传播算法为每个节点分配多个社区标签，实现同时聚类与重叠社区检测。实验结果表明，该方法显著降低说话人分离错误率（DER），在无虚拟语音活动检测（oracle VAD）条件下，于DIHARD-III数据集上达到15.94%的最优性能；在有oracle VAD条件下，更进一步降至11.07%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。