Self-Tuning Spectral Clustering for Speaker Diarization

TL;DR

This paper introduces a novel spectral clustering method, SC-pNA, for speaker diarization that automatically tunes affinity matrices without external data, improving accuracy and efficiency on challenging datasets.

Contribution

The paper proposes SC-pNA, a new pruning algorithm that automatically determines affinity matrix parameters, enhancing spectral clustering for speaker diarization without external tuning.

Findings

Outperforms existing auto-tuning methods on DIHARD-III dataset

Automatically determines affinity matrix parameters from data

More computationally efficient than previous approaches

Abstract

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.