Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation

Domaine:

natural language processing

Type de record:

paper
Créateur:
TakTodWang XinJun
Éditeur:
EurNatNavANR
Éditeur:
CCSD
Hôte:avatar
Submitted to Speaker Odyssey Workshop 2022 The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in the wild. Strategies to improve reliability in the face of uncontrolled, unpredictable attacks are hence needed. We report in this paper our efforts to use self-supervised learning in the form of a wav2vec 2.0 front-end with fine tuning. Despite initial base representations being learned using only bona fide data and no spoofed data, we obtain the lowest equal error rates reported in the literature for both the ASVspoof 2021 Logical Access and Deepfake databases. When combined with data augmentation,these results correspond to an improvement of almost 90% relative to our baseline system.

Visit

hal.science

Tasks

speaker verificationspeech processing

Tags

OYSSEY[INFO.INFO-IA]Computer Science [cs]/Computer Aided Engineering

Similaires

Luganda Dysarthric Automatic Speech Recognition Using Wav2Vec2 and Aggressive Data AugmentationGalaxy detection and identification using deep learning and data augmentationSpeech-to-text model comparison using XLS-R, XLSR-53, and Wav2Vec 2.0ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversionCross-Lingual Transfer Learning for Swahili Automatic Speech Recognition Using Parameterefficient Fine-Tuning and Data AugmentationEmirati Speaker Verification Based on HMM1s, HMM2s, and HMM3s

Luganda Dysarthric Automatic Speech Recognition Using Wav2Vec2 and Aggressive Data Augmentation

We present the first automatic speech recognition (ASR) system specifically designed for Lu

Galaxy detection and identification using deep learning and data augmentation

We present a method for automatic detection and classification of galaxies which includes a novel da

Speech-to-text model comparison using XLS-R, XLSR-53, and Wav2Vec 2.0

Automatic speech recognition (ASR) systems have achieved significant progress in recent years; howev

ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied t

Cross-Lingual Transfer Learning for Swahili Automatic Speech Recognition Using Parameterefficient Fine-Tuning and Data Augmentation

Emirati Speaker Verification Based on HMM1s, HMM2s, and HMM3s

This work focuses on Emirati speaker verification systems in neutral talking environments based on e