papers AI Learner
The Github is limit! Click to go to the new site.

VAE-based regularization for deep speaker embedding

2019-04-07
Yang Zhang, Lantian Li, Dong Wang

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.03617

PDF

http://arxiv.org/pdf/1904.03617


Similar Posts

Comments