# VAE-based regularization for deep speaker embedding

arXiv: https://arxiv.org/abs/1904.03617 · HTML: https://mlsanity.com/paper/1904.03617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

## Built on by (most cited first, 1 of 1)

- [DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion](https://mlsanity.com/paper/2209.04530/) (2022)

## Abstract (arXiv)

Deep speaker embedding has achieved state-of-the-art performance in speaker recognition. A potential problem of these embedded vectors (called `x-vectors') are not Gaussian, causing performance degradation with the famous PLDA back-end scoring. In this paper, we propose a regularization approach based on Variational Auto-Encoder (VAE). This model transforms x-vectors to a latent space where mapped latent codes are more Gaussian, hence more suitable for PLDA scoring.