Speaker recognition with a MLP classifier and LPCC codebook

This paper improves the speaker recognition rates of a MLP classifier and LPCC codebook alone, using a linear combination between both methods. In simulations we have obtained an improvement of 4.7 vectors and 1.5 2.1 complexity of the LPCC-VQ system by a factor of 4.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2021

XMUSPEECH System for VoxCeleb Speaker Recognition Challenge 2021

This paper describes the XMUSPEECH speaker recognition and diarisation s...
research
02/23/2022

Speaker recognition improvement using blind inversion of distortions

In this paper we propose the inversion of nonlinear distortions in order...
research
03/17/2022

Speaker recognition using residual signal of linear and nonlinear prediction models

This Paper discusses the usefulness of the residual signal for speaker r...
research
05/10/2022

Gamified Speaker Comparison by Listening

We address speaker comparison by listening in a game-like environment, h...
research
03/07/2022

Speaker recognition by means of a combination of linear and nonlinear predictive models

This paper deals the combination of nonlinear predictive models with cla...
research
11/14/2019

Deep learning methods in speaker recognition: a review

This paper summarizes the applied deep learning practices in the field o...
research
11/08/2018

Gaussian-Constrained training for speaker verification

Neural models, in particular the d-vector and x-vector architectures, ha...

Please sign up or login with your details

Forgot password? Click here to reset