Investigation of Sub-Band Discriminative Information Between Spoofed and Genuine Speech

  title={Investigation of Sub-Band Discriminative Information Between Spoofed and Genuine Speech},
  author={Kaavya Sriskandaraja and Vidhyasaharan Sethu and Phu Ngoc Le and Eliathamby Ambikairajah},
A speaker verification system should include effective precautions against malicious spoofing attacks, and although some initial countermeasures have been recently proposed, this remains a challenging research problem. This paper investigates discrimination between spoofed and genuine speech, as a function of frequency bands, across the speech bandwidth. Findings from our investigation inform some proposed filter bank design approaches for discrimination of spoofed speech. Experiments are… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Experiments are conducted on the Spoofing and Anti-Spoofing (SAS) corpus using the proposed frequency-selective approach demonstrates an 11% relative improvement in terms of equal error rate compared with a conventional mel filter bank.


Publications citing this paper.
Showing 1-9 of 9 extracted citations


Publications referenced by this paper.
Showing 1-10 of 27 references

Automatic speaker verification spoofing and countermeasures challenge evaluation plan

  • J. Epps, A. Khodabakhsh Z. Wu, +9 authors N. Evans
  • MATLAB : optimization toolbox : user ' s guide…
  • 2015

Spectral shifting of speaker-specific information for narrow band telephonic speaker recognition

  • T. Thiruvaran, V. Sethu, E. Ambikairajah, H. Li
  • Electronics Letters, vol. 51, pp. 2149-2151, 2015…
  • 2015
3 Excerpts

Spoofing and Anti-Spoofing: A Shared View of Speaker Verification, Speech Synthesis and Voice Conversion

  • Z. Wu, T. Kinnunen, N. Evans, J. Yamagishi
  • Asia-Pacific Signal and Information Processing…
  • 2015
1 Excerpt

Similar Papers

Loading similar papers…