ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

dc.contributor.affiliationNational Institute of Informatics - Wang, Xin
dc.contributor.affiliationNuance Communications Inc - Delgado, Héctor
dc.contributor.affiliationPindrop - Tak, Hemlata
dc.contributor.affiliationApple - Jung, Jee-weon
dc.contributor.affiliationCarnegie Mellon University - Shim, Hyejin
dc.contributor.affiliationEURECOM - Todisco, Massimiliano
dc.contributor.affiliationKLASS - Kukanov, Ivan
dc.contributor.affiliationNational Institute of Informatics - Liu, Xuechen
dc.contributor.affiliationTCG Crest - Sahidullah, Md
dc.contributor.affiliationUniversity of Eastern Finland - Kinnunen, Tomi
dc.contributor.affiliationEURECOM - Evans, Nicholas
dc.contributor.affiliationThe Hong Kong Polytechnic University - Lee, Kong Aik
dc.contributor.affiliationNational Institute of Informatics - Yamagishi, Junichi
dc.contributor.affiliationSeoul National University - Jeong, Myeonghun
dc.contributor.affiliationUniversity of Rochester - Zhu, Ge
dc.contributor.affiliationUniversity of Rochester - Zang, Yongyi
dc.contributor.affiliationUniversity of Rochester - Zhang, Neil
dc.contributor.affiliationCarnegie Mellon University - Maiti, Soumi
dc.contributor.affiliationUniversity of Stuttgart - Lux, Florian
dc.contributor.affiliationFraunhofer Institute for Applied and Integrated Security - Muller, Nicolas
dc.contributor.affiliationShanghai Jiao Tong University - Zhang, Wangyou
dc.contributor.affiliationUniversity at Buffalo - Sun, Chengzhe
dc.contributor.affiliationUniversity at Buffalo - Hou, Shuwei
dc.contributor.affiliationUniversity at Buffalo - Lyu, Siwei
dc.contributor.affiliationUniversity of Helsinki - Le Maguer, Sebastien
dc.contributor.affiliationTianjin University - Gong, Cheng
dc.contributor.affiliationUniversity of Science and Technology of China - Guo, Hanjie
dc.contributor.affiliationUniversity of Science and Technology of China - Chen, Liping
dc.contributor.affiliationUniversity of Eastern Finland - Singh, Vishwanath
dc.contributor.authorWang, Xin
dc.contributor.authorDelgado, Héctor
dc.contributor.authorTak, Hemlata
dc.contributor.authorJung, Jee-weon
dc.contributor.authorShim, Hyejin
dc.contributor.authorTodisco, Massimiliano
dc.contributor.authorKukanov, Ivan
dc.contributor.authorLiu, Xuechen
dc.contributor.authorSahidullah, Md
dc.contributor.authorKinnunen, Tomi
dc.contributor.authorEvans, Nicholas
dc.contributor.authorLee, Kong Aik
dc.contributor.authorYamagishi, Junichi
dc.contributor.authorJeong, Myeonghun
dc.contributor.authorZhu, Ge
dc.contributor.authorZang, Yongyi
dc.contributor.authorZhang, Neil
dc.contributor.authorMaiti, Soumi
dc.contributor.authorLux, Florian
dc.contributor.authorMuller, Nicolas
dc.contributor.authorZhang, Wangyou
dc.contributor.authorSun, Chengzhe
dc.contributor.authorHou, Shuwei
dc.contributor.authorLyu, Siwei
dc.contributor.authorLe Maguer, Sebastien
dc.contributor.authorGong, Cheng
dc.contributor.authorGuo, Hanjie
dc.contributor.authorChen, Liping
dc.contributor.authorSingh, Vishwanath
dc.date.accessioned2025-03-24T15:26:51Z
dc.date.issued2024-12-18
dc.date.issued2024-12-18
dc.description  This is the Zenodo repository for the ASVspoof 5 database. ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previous challenges, the ASVspoof~5 database is built from crowdsourced data collected from around 2,000 speakers in diverse acoustic conditions.  More than 20 attacks, also crowdsourced, are generated and optionally tested using surrogate detection models, while seven adversarial attacks are incorporated for the first time. Please check README.txt and LICENSE.txt before downloading the database. Database paper (to be submitted): https://arxiv.org/abs/2502.08857 Please consider citing the reference listed at the bottom of this page. It is highly recommended to follow the rules and instructions in the ASVspoof 5 challenge evaluation plan (phase 2, https://www.asvspoof.org/), if you want to produce results comparable with the literature.  Latest work using the ASVspoof 5 database can be found in the Automatic Speaker Verification Spoofing Countermeasures Workshop proceeding: https://www.isca-archive.org/asvspoof_2024/index.html If you are interested in creating spoofed data for research purpose using the ASVspoof 5 protocol, please send request to info@asvspoof.org
dc.identifierhttps://doi.org/10.5281/zenodo.14498691
dc.identifier.urihttps://hydatakatalogi-test-24.it.helsinki.fi/handle/123456789/11605
dc.rightsOpen
dc.rights.licenseodc-by
dc.subjectanti-spoofing
dc.subjectpresentation attack detection
dc.subjectspeech deepfake detection
dc.titleASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
dc.typedataset
dc.typedataset

Files

Repositories