STUDY OF VOICE VERIFICATION SYSTEM TOLERANCE TO SPOOFING ATTACKS USING A TEXT-TO-SPEECH SYSTEM
ITMO University, Department of Speech Information Systems; Post-Graduate Student
K. . Simonchik
«Speech Technology Center» Ltd., Saint Petersburg National Research University of Information Technologies, Mechanics and Optics; Head of section, Associated Professor
Abstract. A method of spoofing text-dependent voice verification system based on the most popular TTS approaches (Unit Selection and HMM) is presented. The method is shown to allow for false acceptance error of 98—100 % in the case of sufficiently large TTS database. A distinctive feature of the method is that it can be fully automated if used in conjunction with a speech recognition system.
Keywords: spoofing, speech synthesis, speaker recognition