In plain words: A collection of real voice commands and replayed copies, recorded through four voice assistant kits with different microphones across varied noise and speaker positions. It is the first public database built to test protection of modern voice-controlled systems against replay attacks in realistic settings.
Abstract
This paper introduces a new database of voice recordings with the goal of supporting research on vulnerabilities and protection of voice-controlled systems (VCSs). In contrast to prior efforts, the proposed database contains both genuine voice commands and replayed recordings of such commands, collected in realistic VCSs usage scenarios and using modern voice assistant development kits. Specifically, the database contains recordings from four systems (each with a different microphone array) in a variety of environmental conditions with different forms of background noise and relative positions between speaker and device. To the best of our knowledge, this is the first publicly available database that has been specifically designed for the protection of state-of-the-art voice-controlled systems against various replay attacks in various conditions and environments.
Yuan Gong, Jian Yang, Jacob Huber, Mitchell MacKnight, Christian Poellabauer
arXiv:1904.03365 · cs.CR, cs.LG, cs.SD, eess.AS · submitted Apr 6, 2019 · updated Jul 2, 2019
abstract · pdf · html · To appear in Interspeech 2019. Data set available at https://github.com/YuanGongND/ReMASC