For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Voice Liveness Detection Based on Phoneme Information-based Pop-noise Detector
Shihono MOCHIZUKI Sayaka SHIOTA Hitoshi KIYA
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)
Publication Date: 2018/03/01
Online ISSN: 1881-0225
Type of Manuscript: Special Section PAPER (Special Section on Student Research)
speaker verification, detecting pop-noise, voice liveness detection, phoneme information,
Full Text(in Japanese): PDF(2.8MB)
>>Buy this Article
This paper proposes a pop-noise (PN) detection method considering phoneme information for anti-spoofing countermeasure of speaker verification. Recently, many countermeasures against spoofing attacks have been reported. As one of fundamental solutions, voice liveness detection (VLD) framework and PN detection methods have been proposed. The VLD framework identifies whether an input sample is uttered by a genuine voice or played via a loudspeaker. This paper proposes a PN detector using phoneme balance in order to improve the accuracy of the PN detection method. As a result, it is shown that the proposed method is reliable countermeasure for anti-spoofing.