# Toroidal Probabilistic Spherical Discriminant Analysis

arXiv: https://arxiv.org/abs/2210.15441 · HTML: https://mlsanity.com/paper/2210.15441/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 7 of 7)

- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [BUT System Description to VoxCeleb Speaker Recognition Challenge 2019](https://mlsanity.com/paper/1910.12592/) (2019)
- [The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021](https://mlsanity.com/paper/2109.01989/) (2021)
- [The 2021 NIST Speaker Recognition Evaluation](https://mlsanity.com/paper/2204.10242/) (2022)
- [Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch](https://mlsanity.com/paper/2203.10300/) (2022)
- [NIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition](https://mlsanity.com/paper/2108.07118/) (2021)
- [Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings](https://mlsanity.com/paper/2203.14893/) (2022)

## Abstract (arXiv)

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 accuracy 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.