DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Jiawei, Lin, I-Ming, Chiu, I-Hsiang, Chen, Xuanjun, Wu, Haibin, Ren, Wenze, Tsao, Yu, Lee, Hung-yi, Jang, Jyh-Shing Roger
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916392859598848
author Du, Jiawei
Lin, I-Ming
Chiu, I-Hsiang
Chen, Xuanjun
Wu, Haibin
Ren, Wenze
Tsao, Yu
Lee, Hung-yi
Jang, Jyh-Shing Roger
author_facet Du, Jiawei
Lin, I-Ming
Chiu, I-Hsiang
Chen, Xuanjun
Wu, Haibin
Ren, Wenze
Tsao, Yu
Lee, Hung-yi
Jang, Jyh-Shing Roger
contents Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) dataset. The DFADD dataset collected the deepfake audio based on advanced diffusion and flowmatching TTS models. Additionally, we reveal that current anti-spoofing models lack sufficient robustness against highly human-like audio generated by diffusion and flow-matching TTS systems. The proposed DFADD dataset addresses this gap and provides a valuable resource for developing more resilient anti-spoofing models.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08731
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset
Du, Jiawei
Lin, I-Ming
Chiu, I-Hsiang
Chen, Xuanjun
Wu, Haibin
Ren, Wenze
Tsao, Yu
Lee, Hung-yi
Jang, Jyh-Shing Roger
Sound
Audio and Speech Processing
Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) dataset. The DFADD dataset collected the deepfake audio based on advanced diffusion and flowmatching TTS models. Additionally, we reveal that current anti-spoofing models lack sufficient robustness against highly human-like audio generated by diffusion and flow-matching TTS systems. The proposed DFADD dataset addresses this gap and provides a valuable resource for developing more resilient anti-spoofing models.
title DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.08731