Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
SILNOVA, A. BRUMMER, J. SWART, A. BURGET, L.
Originální název
Toroidal Probabilistic Spherical Discriminant Analysis
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
n 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 infe- rior. On NIST SRE'21 we find that T-PSDA gives large accu- racy gains compared to both cosine scoring and PLDA.
Klíčová slova
speaker recognition, PSDA, Von Mises-Fishe
Autoři
SILNOVA, A.; BRUMMER, J.; SWART, A.; BURGET, L.
Vydáno
4. 6. 2023
Nakladatel
IEEE Signal Processing Society
Místo
Rhodes Island
ISBN
978-1-7281-6327-7
Kniha
Proceedings of ICASSP 2023
Strany od
1
Strany do
5
Strany počet
URL
https://ieeexplore.ieee.org/document/10095580
BibTex
@inproceedings{BUT185199, author="Anna {Silnova} and Johan Nikolaas Langenhoven {Brummer} and Albert du Preez {Swart} and Lukáš {Burget}", title="Toroidal Probabilistic Spherical Discriminant Analysis", booktitle="Proceedings of ICASSP 2023", year="2023", pages="1--5", publisher="IEEE Signal Processing Society", address="Rhodes Island", doi="10.1109/ICASSP49357.2023.10095580", isbn="978-1-7281-6327-7", url="https://ieeexplore.ieee.org/document/10095580" }