Compact Speaker Embedding: lrx-vector

08/11/2020
by   Munir Georges, et al.
0

Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for training the lrx-vector system and compare against low-rank factorization with SVD. On the VOiCES 2019 far-field corpus we were able to reduce the weights by 28 recognition rate constant (1.83

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2020

Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification

Modern deep neural networks (DNNs) often require high memory consumption...
research
10/25/2019

Structural sparsification for Far-field Speaker Recognition with GNA

Recently, deep neural networks (DNN) have been widely used in speaker re...
research
09/25/2018

Attention Mechanism in Speaker Recognition: What Does It Learn in Deep Speaker Embedding?

This paper presents an experimental study on deep speaker embedding with...
research
08/12/2021

Xi-Vector Embedding for Speaker Recognition

We present a Bayesian formulation for deep speaker embedding, wherein th...
research
06/28/2015

Improved Deep Speaker Feature Learning for Text-Dependent Speaker Recognition

A deep learning approach has been proposed recently to derive speaker id...
research
04/05/2019

Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition

In this work, we continue in our research on i-vector extractor for spea...
research
07/28/2020

Siamese x-vector reconstruction for domain adapted speaker recognition

With the rise of voice-activated applications, the need for speaker reco...

Please sign up or login with your details

Forgot password? Click here to reset