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

AK Sarkar, ZH Tan - Acoustics, 2023 - mdpi.com
Deep representation learning has gained significant momentum in advancing text-
dependent speaker verification (TD-SV) systems. When designing deep neural networks …

A comparison of CQT spectrogram with STFT-based acoustic features in Deep Learning-based synthetic speech detection

P Abdzadeh, H Veisi - Journal of AI and Data Mining, 2023 - jad.shahroodut.ac.ir
Automatic Speaker Verification (ASV) systems have proven to bevulnerable to various types
of presentation attacks, among whichLogical Access attacks are manufactured using …

Vocal tract length perturbation for text-dependent speaker verification with autoregressive prediction coding

ZH Tan - IEEE Signal Processing Letters, 2021 - ieeexplore.ieee.org
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 …

ASTT: acoustic spatial-temporal transformer for short utterance speaker recognition

X Wu, R Li, B Deng, M Zhao, X Du, J Wang… - Multimedia Tools and …, 2023 - Springer
Abstract Text-independent Short Utterance Speaker Recognition (SUSR) is of importance for
the purpose of person authentication. However, it is a great challenge for the speaker …

Shouted and whispered speech compensation for speaker verification systems

S Prieto, A Ortega, I López-Espejo, E Lleida - Digital Signal Processing, 2022 - Elsevier
Nowadays, speaker verification systems begin to perform very well under normal speech
conditions due to the plethora of neutrally-phonated speech data available, which are used …

Self-segmentation of pass-phrase utterances for deep feature learning in text-dependent speaker verification

AK Sarkar, ZH Tan - Computer Speech & Language, 2021 - Elsevier
In this paper, we propose a novel method to segment and label pass-phrase utterances for
training deep neural network (DNN) bottleneck (BN) features for text-dependent speaker …

On training targets and activation functions for deep representation learning in text-dependent speaker verification

ZH Tan - arxiv preprint arxiv:2201.06426, 2022 - arxiv.org
Deep representation learning has gained significant momentum in advancing text-
dependent speaker verification (TD-SV) systems. When designing deep neural networks …

[PDF][PDF] Advances in Deep Speaker Verification: a study on robustness, portability, and security

X Liu - 2023 - erepo.uef.fi
Automatic speaker verification has numerous studies widely used in applications such as
user authentication, access control, and smart assistants. Empowered by stronger hardware …

Contributions to speech processing and ambient sound analysis

R Serizel - 2022 - inria.hal.science
We are constantly surrounded by sounds that we continuously exploit to adapt our actions to
situations we are facing. Some of the sounds like speech can have a particular structure …

[引用][C] Habilitation à diriger des recherches

R Serizel - 2022 - Johns Hopkins University, Baltimore …