Augmentation through Laundering Attacks for Audio Spoof Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ali, Hashim, Subramani, Surya, Malik, Hafiz
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914009863684096
author Ali, Hashim
Subramani, Surya
Malik, Hafiz
author_facet Ali, Hashim
Subramani, Surya
Malik, Hafiz
contents Recent text-to-speech (TTS) developments have made voice cloning (VC) more realistic, affordable, and easily accessible. This has given rise to many potential abuses of this technology, including Joe Biden's New Hampshire deepfake robocall. Several methodologies have been proposed to detect such clones. However, these methodologies have been trained and evaluated on relatively clean databases. Recently, ASVspoof 5 Challenge introduced a new crowd-sourced database of diverse acoustic conditions including various spoofing attacks and codec conditions. This paper is our submission to the ASVspoof 5 Challenge and aims to investigate the performance of Audio Spoof Detection, trained using data augmentation through laundering attacks, on the ASVSpoof 5 database. The results demonstrate that our system performs worst on A18, A19, A20, A26, and A30 spoofing attacks and in the codec and compression conditions of C08, C09, and C10.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01108
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Augmentation through Laundering Attacks for Audio Spoof Detection
Ali, Hashim
Subramani, Surya
Malik, Hafiz
Audio and Speech Processing
Artificial Intelligence
Sound
Recent text-to-speech (TTS) developments have made voice cloning (VC) more realistic, affordable, and easily accessible. This has given rise to many potential abuses of this technology, including Joe Biden's New Hampshire deepfake robocall. Several methodologies have been proposed to detect such clones. However, these methodologies have been trained and evaluated on relatively clean databases. Recently, ASVspoof 5 Challenge introduced a new crowd-sourced database of diverse acoustic conditions including various spoofing attacks and codec conditions. This paper is our submission to the ASVspoof 5 Challenge and aims to investigate the performance of Audio Spoof Detection, trained using data augmentation through laundering attacks, on the ASVSpoof 5 database. The results demonstrate that our system performs worst on A18, A19, A20, A26, and A30 spoofing attacks and in the codec and compression conditions of C08, C09, and C10.
title Augmentation through Laundering Attacks for Audio Spoof Detection
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2410.01108