ASVspoof 2019 database


This page only hosts audio samples from ASVspoof2019 LA database.

ASVspoof 2019 database comes with The Open Data Commons Attribution License. Please follow the license when using samples on this webpage.

Please cite the following papers if you use ASVspoof 2019 database for your research:

Todisco, M. et al. ASVspoof 2019: future horizons in spoofed and fake audio detection. in Proc. Interspeech 1008–1012 (2019). doi:10.21437/Interspeech.2019-2249

Wang, X. et al. ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech. Comput. Speech Lang. 64, 101114 (2020), doi:10.1016/j.csl.2020.101114

Spoofing systems

An updated list of spoofing systems can be found in the published paper.

Picture not found

Audio samples

LA evaluation set

TTS VC (TTS speech -> target speech) TTS Bona-fide VC (source speech -> target speech) Bona-fide
A07 A08 A09 A10 A11 A12 A13 A14 A15 A16 target A17 A18 A19 source

LA dev/train set

TTS Bona-fide VC (source speech -> target speech) Bona-fide
A01 A02 A03 A04 targt A05 A06 source