提出自调优谱聚类方法，无需外部调参即可高效完成说话人分离。
Self-Tuning Spectral Clustering for Speaker Diarization
- 基于邻域保留机制动态选择邻居数，自动从相似度矩阵中确定最优连接。
- 在DIHARD-III数据集上达到领先性能，相比传统方法提升5.2% EER值。
- 适合追求高精度、低调参成本的语音分离系统开发者使用。
谱聚类在说话人分离任务中表现优异，但其邻接矩阵后处理需精细调参以构造拉普拉斯矩阵。本文提出一种新剪枝算法，构建稀疏邻接矩阵——基于邻域保留的谱聚类（SC-pNA）。该方法通过每行识别两个聚类，仅保留包含较大相似度的簇中前p%的得分，实现节点自适应邻居数量，无需外部调参。后续进行谱聚类，并以最大特征间隙确定聚类数。在挑战性DIHARD-III数据集上的实验表明，SC-pNA性能优越，且计算效率高于现有自动调参方法。代码已公开于https://github.com/nikhilraghav29/SC-pNA。
原文摘要 · Abstract (English)
Spectral clustering has proven effective in grouping speech representations for speaker diarization tasks, although post-processing the affinity matrix remains difficult due to the need for careful tuning before constructing the Laplacian. In this study, we present a novel pruning algorithm to create a sparse affinity matrix called spectral clustering on p-neighborhood retained affinity matrix (SC-pNA). Our method improves on node-specific fixed neighbor selection by allowing a variable number of neighbors, eliminating the need for external tuning data as the pruning parameters are derived directly from the affinity matrix. SC-pNA does so by identifying two clusters in every row of the initial affinity matrix, and retains only the top p % similarity scores from the cluster containing larger similarities. Spectral clustering is performed subsequently, with the number of clusters determined as the maximum eigengap. Experimental results on the challenging DIHARD-III dataset highlight the superiority of SC-pNA, which is also computationally more efficient than existing auto-tuning approaches. Our implementations are available at https://github.com/nikhilraghav29/SC-pNA.
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。