Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jung, Jee-weon, Wu, Yihan, Wang, Xin, Kim, Ji-Hoon, Maiti, Soumi, Matsunaga, Yuta, Shim, Hye-jin, Tian, Jinchuan, Evans, Nicholas, Chung, Joon Son, Zhang, Wangyou, Um, Seyun, Takamichi, Shinnosuke, Watanabe, Shinji
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.17285
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910911393955840
author Jung, Jee-weon
Wu, Yihan
Wang, Xin
Kim, Ji-Hoon
Maiti, Soumi
Matsunaga, Yuta
Shim, Hye-jin
Tian, Jinchuan
Evans, Nicholas
Chung, Joon Son
Zhang, Wangyou
Um, Seyun
Takamichi, Shinnosuke
Watanabe, Shinji
author_facet Jung, Jee-weon
Wu, Yihan
Wang, Xin
Kim, Ji-Hoon
Maiti, Soumi
Matsunaga, Yuta
Shim, Hye-jin
Tian, Jinchuan
Evans, Nicholas
Chung, Joon Son
Zhang, Wangyou
Um, Seyun
Takamichi, Shinnosuke
Watanabe, Shinji
contents This paper introduces SpoofCeleb, a dataset designed for Speech Deepfake Detection (SDD) and Spoofing-robust Automatic Speaker Verification (SASV), utilizing source data from real-world conditions and spoofing attacks generated by Text-To-Speech (TTS) systems also trained on the same real-world data. Robust recognition systems require speech data recorded in varied acoustic environments with different levels of noise to be trained. However, current datasets typically include clean, high-quality recordings (bona fide data) due to the requirements for TTS training; studio-quality or well-recorded read speech is typically necessary to train TTS models. Current SDD datasets also have limited usefulness for training SASV models due to insufficient speaker diversity. SpoofCeleb leverages a fully automated pipeline we developed that processes the VoxCeleb1 dataset, transforming it into a suitable form for TTS training. We subsequently train 23 contemporary TTS systems. SpoofCeleb comprises over 2.5 million utterances from 1,251 unique speakers, collected under natural, real-world conditions. The dataset includes carefully partitioned training, validation, and evaluation sets with well-controlled experimental protocols. We present the baseline results for both SDD and SASV tasks. All data, protocols, and baselines are publicly available at https://jungjee.github.io/spoofceleb.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17285
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
Jung, Jee-weon
Wu, Yihan
Wang, Xin
Kim, Ji-Hoon
Maiti, Soumi
Matsunaga, Yuta
Shim, Hye-jin
Tian, Jinchuan
Evans, Nicholas
Chung, Joon Son
Zhang, Wangyou
Um, Seyun
Takamichi, Shinnosuke
Watanabe, Shinji
Sound
Artificial Intelligence
Audio and Speech Processing
This paper introduces SpoofCeleb, a dataset designed for Speech Deepfake Detection (SDD) and Spoofing-robust Automatic Speaker Verification (SASV), utilizing source data from real-world conditions and spoofing attacks generated by Text-To-Speech (TTS) systems also trained on the same real-world data. Robust recognition systems require speech data recorded in varied acoustic environments with different levels of noise to be trained. However, current datasets typically include clean, high-quality recordings (bona fide data) due to the requirements for TTS training; studio-quality or well-recorded read speech is typically necessary to train TTS models. Current SDD datasets also have limited usefulness for training SASV models due to insufficient speaker diversity. SpoofCeleb leverages a fully automated pipeline we developed that processes the VoxCeleb1 dataset, transforming it into a suitable form for TTS training. We subsequently train 23 contemporary TTS systems. SpoofCeleb comprises over 2.5 million utterances from 1,251 unique speakers, collected under natural, real-world conditions. The dataset includes carefully partitioned training, validation, and evaluation sets with well-controlled experimental protocols. We present the baseline results for both SDD and SASV tasks. All data, protocols, and baselines are publicly available at https://jungjee.github.io/spoofceleb.
title SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2409.17285