Conventional methods for speaker diarization involve windowing an audio file into short segments to extract speaker embeddings, followed by an unsupervised clustering of the embeddings. This multi-step approach generates speaker assignments for each segment. In this paper, we propose a novel Supervised HierArchical gRaph Clustering algorithm (SHARC) for speaker diarization where we introduce a hierarchical structure using Graph Neural Network (GNN) to perform supervised clustering. The supervision allows the model to update the representations and directly improve the clustering performance, thus enabling a single-step approach for diarization. In the proposed work, the input segment embeddings are treated as nodes of a graph with the edge weights corresponding to the similarity scores between the nodes. We also propose an approach to jointly update the embedding extractor and the GNN model to perform end-to-end speaker diarization (E2E-SHARC). During inference, the hierarchical clustering is performed using node densities and edge existence probabilities to merge the segments until convergence. In the diarization experiments, we illustrate that the proposed E2E-SHARC approach achieves 53% and 44% relative improvements over the baseline systems on benchmark datasets like AMI and Voxconverse, respectively.

翻译：传统说话人日志方法通常将音频文件分段以提取说话人嵌入，随后对嵌入执行无监督聚类。这种多步骤方法为每个片段生成说话人分配。本文提出一种新颖的监督层次图聚类算法（SHARC）用于说话人日志，通过引入基于图神经网络（GNN）的层次结构实现监督聚类。监督机制使模型能够更新表征并直接提升聚类性能，从而实现日志任务的单步化方法。在所提出的工作中，输入片段嵌入被视为图的节点，边权重对应节点间的相似度分数。我们还提出一种联合更新嵌入提取器与GNN模型的方法，以执行端到端说话人日志（E2E-SHARC）。推理过程中，利用节点密度与边存在概率进行层次聚类，直至片段合并收敛。在日志实验中，我们证明所提出的E2E-SHARC方法在AMI和Voxconverse等基准数据集上相比基线系统分别实现了53%和44%的相对性能提升。