Skip to Main content Skip to Navigation
Journal articles

ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

Xin Wang 1, 2 Junichi Yamagishi 3 Massimiliano Todisco 3 Héctor Delgado 3 Andreas Nautsch 3 Nicholas Evans 3 Md Sahidullah 4 Ville Vestman 5 Tomi Kinnunen 5 Kong Aik Lee 6 Lauri Juvela 7 Paavo Alku 7 Yu-Huai Peng 8 Hsin-Te Hwang 8 Yu Tsao 8 Hsin-Min Wang 8 Sébastien Le Maguer 9 Markus Becker 10 Fergus Henderson 10 Rob Clark 10 Yu Zhang 10 Quan Wang 10 Ye Jia 10 Kai Onuma 11 Koji Mushika 11 Takashi Kaneda 11 Yuan Jiang 12 Li-Juan Liu 12 Yi-Chiao Wu 13 Wen-Chin Huang 13 Tomoki Toda 13 Kou Tanaka 14 Hirokazu Kameoka 14 Ingmar Steiner 15 Driss Matrouf 16 Jean-François Bonastre 16 Avashna Govender 17 Srikanth Ronanki 17 Jing-Xuan Zhang 18 Zhen-Hua Ling 18 
Abstract : Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately , just like all other biometric systems, ASV is vulnerable to spoofing, also referred to as "presentation attacks." These vulnerabilities are generally unacceptable and call for spoofing countermeasures or "presentation attack detection" systems. In addition to impersonation, ASV systems are vulnerable to replay, speech synthesis, and voice conversion attacks. The ASVspoof challenge initiative was created to foster research on anti-spoofing and to provide common platforms for the assessment and comparison of spoofing countermeasures. The first edition, ASVspoof 2015, focused upon the study of countermeasures for detecting of text-to-speech synthesis (TTS) and voice conversion (VC) attacks. The second edition, ASVspoof 2017, focused instead upon replay spoofing attacks and countermeasures. The ASVspoof 2019 edition is the first to consider all three spoofing attack types within a single challenge. While they originate from the same source database and same underlying protocol, they are explored in two specific use case scenarios. Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques. Replay spoofing attacks within a physical access (PA) scenario are generated through carefully controlled simulations that support much more revealing analysis than possible previously. Also new to the 2019 edition is the use of the tandem detection cost function metric, which reflects the impact of spoofing and countermeasures on the reliability of a fixed ASV system. This paper describes the database design, protocol, spoofing attack implementations, and baseline ASV and countermeasure results. It also describes a human assessment on spoofed data in logical access. It was demonstrated that the spoofing data in the ASVspoof 2019 database have varied degrees of perceived quality and similarity to the target speakers, including spoofed data that cannot be differentiated from bona fide utterances even by human subjects. It is expected that the ASVspoof 2019 database, with its varied coverage of different types of spoofing data, could further foster research on anti-spoofing.
Complete list of metadata

Cited literature [72 references]  Display  Hide  Download
Contributor : Md Sahidullah Connect in order to contact the contributor
Submitted on : Tuesday, September 22, 2020 - 12:53:22 PM
Last modification on : Friday, July 8, 2022 - 10:05:34 AM
Long-term archiving on: : Friday, December 4, 2020 - 8:28:05 PM


Files produced by the author(s)



Xin Wang, Junichi Yamagishi, Massimiliano Todisco, Héctor Delgado, Andreas Nautsch, et al.. ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech. Computer Speech and Language, Elsevier, 2020, 64, pp.101114. ⟨10.1016/j.csl.2020.101114⟩. ⟨hal-02945493⟩



Record views


Files downloads