Self-Tuning Spectral Clustering for Speaker Diarization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Raghav, Nikhil, Gupta, Avisek, Sahidullah, Md, Das, Swagatam
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913875904954368
author Raghav, Nikhil
Gupta, Avisek
Sahidullah, Md
Das, Swagatam
author_facet Raghav, Nikhil
Gupta, Avisek
Sahidullah, Md
Das, Swagatam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00023
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Tuning Spectral Clustering for Speaker Diarization
Raghav, Nikhil
Gupta, Avisek
Sahidullah, Md
Das, Swagatam
Signal Processing
Machine Learning
Sound
Audio and Speech Processing
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.
title Self-Tuning Spectral Clustering for Speaker Diarization
topic Signal Processing
Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.00023