Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding

by   Achintya kr. Sarkar, et al.

In this letter, we propose a vocal tract length (VTL) perturbation method for text-dependent speaker verification (TD-SV), in which a set of TD-SV systems are trained, one for each VTL factor, and score-level fusion is applied to make a final decision. Next, we explore the bottleneck (BN) feature extracted by training deep neural networks with a self-supervised objective, autoregressive predictive coding (APC), for TD-SV and compare it with the well-studied speaker-discriminant BN feature. The proposed VTL method is then applied to APC and speaker-discriminant BN features. In the end, we combine the VTL perturbation systems trained on MFCC and the two BN features in the score domain. Experiments are performed on the RedDots challenge 2016 database of TD-SV using short utterances with Gaussian mixture model-universal background model and i-vector techniques. Results show the proposed methods significantly outperform the baselines.


page 1

page 2

page 3

page 4


On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors

Applying x-vectors for speaker verification has recently attracted great...

On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification

Deep representation learning has gained significant momentum in advancin...

Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification

The performance of speaker-related systems usually degrades heavily in p...

Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification

In this paper, we propose a novel method that trains pass-phrase specifi...

Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification

In this paper, we propose a novel way of addressing text-dependent autom...

Quality Measures for Speaker Verification with Short Utterances

The performances of the automatic speaker verification (ASV) systems deg...

Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification

There are a number of studies about extraction of bottleneck (BN) featur...