# Jeffreys divergence-based regularization of neural network output distribution applied to speaker recognition

arXiv: https://arxiv.org/abs/2312.16885 · HTML: https://mlsanity.com/paper/2312.16885/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2023.

## Built on by (most cited first, 2 of 2)

- [Constrained Paraphrase Consistency for LLM Hallucination Detection](https://mlsanity.com/paper/2606.08158/) (2026)
- [Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification](https://mlsanity.com/paper/2606.22369/) (2026)

## Abstract (arXiv)

A new loss function for speaker recognition with deep neural network is proposed, based on Jeffreys Divergence. Adding this divergence to the cross-entropy loss function allows to maximize the target value of the output distribution while smoothing the non-target values. This objective function provides highly discriminative features. Beyond this effect, we propose a theoretical justification of its effectiveness and try to understand how this loss function affects the model, in particular the impact on dataset types (i.e. in-domain or out-of-domain w.r.t the training corpus). Our experiments show that Jeffreys loss consistently outperforms the state-of-the-art for speaker recognition, especially on out-of-domain data, and helps limit false alarms.