Replay attack detection using variable-frequency resolution phase and magnitude features

Meng Liu, Longbiao Wang, Jianwu Dang, Kong Aik Lee, Seiichi Nakagawa

Research output: Journal article publicationJournal articleAcademic researchpeer-review

6 Citations (Scopus)

Abstract

Replay attacks pose the most severe threat to automatic speaker verification systems among various spoofing attacks. In this paper, we propose a novel feature extraction method that leverages both the phase-based and magnitude-based features. The proposed method fully utilizes the subband information and the complementary information from the phase and magnitude spectra. First, we conduct a discriminative performance analysis on full frequency bands via the F-ratio method. Then, variable-frequency resolution features are extracted via several techniques to capture highly discriminative information on frequency bands. Finally, complementary information from the phase and magnitude domains are fused to achieve higher performance. The results on the ASVspoof 2017 database demonstrate that our proposed frequency adaptive features attain relative error reduction rates of 83.4% and 62.3% on the development and evaluation datasets, respectively, compared to the baseline method.

Original languageEnglish
Article number101161
JournalComputer Speech and Language
Volume66
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes

Keywords

  • Adaptive features
  • Discriminative information
  • Frequency modulation
  • Replay attack

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Replay attack detection using variable-frequency resolution phase and magnitude features'. Together they form a unique fingerprint.

Cite this