# Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood

arXiv: https://arxiv.org/abs/2610.06691 · HTML: https://mlsanity.com/paper/2610.06691/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 32 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 2 of 2)

- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)

## Abstract (arXiv)

Embedding enhancement improves speaker verification under acoustic mismatch without modifying a frozen backbone. Recent work has established a practical label-free setting for this task, but often adopts increasingly structured formulations. Here, the clean target is directly observed during training, making enhancement a matching problem on the unit hypersphere. We model the clean target with a von Mises--Fisher (vMF) likelihood and profile out a sample-wise concentration parameter, yielding a simple closed-form objective with adaptive weighting. Across VoxCeleb1, VoxSRC23, CN-Celeb, VOiCES, and VC-Mix, the proposed method largely preserves the baseline and gives clearer gains on challenging mismatch sets. It also remains stable under a broad single-view recipe, where a recent diffusion baseline becomes less reliable in controlled comparisons. These results suggest that effective label-free embedding enhancement in this setting does not require a highly structured formulation.