Toroidal Probabilistic Spherical Discriminant Analysis
Anna Silnova, Niko Brümmer, Albert Swart, Lukás Burget
Abstract
In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring back-ends are commonly used, namely cosine scoring and PLDA. We have recently proposed PSDA, an analog to PLDA that uses Von Mises-Fisher distributions instead of Gaussians. In this paper, we present toroidal PSDA (T-PSDA). It extends PSDA with the ability to model within and between-speaker variabilities in toroidal submanifolds of the hypersphere. Like PLDA and PSDA, the model allows closed-form scoring and closed-form EM updates for training. On VoxCeleb, we find T-PSDA accu-racy on par with cosine scoring, while PLDA accuracy is inferior. On NIST SRE’21 we find that T-PSDA gives large accuracy gains compared to both cosine scoring and PLDA.<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
BibTeX
@inproceedings{icassp2023_toroidalprobabil,
title = {Toroidal Probabilistic Spherical Discriminant Analysis},
author = {Anna Silnova and Niko Brümmer and Albert Swart and Lukás Burget},
booktitle = {ICASSP 2023},
year = {2023}
}