Skip to Main content Skip to Navigation
Conference papers

Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems

Abstract : Automatic speaker verification (ASV) systems use a play-back detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and played-back speech, it may be possible to degrade their performance by transforming the acoustic characteristics of the played-back speech close to that of the genuine speech. One way to do this is to enhance speech "stolen" from the target speaker before playback. We tested the effectiveness of a playback attack using this method by using the speech enhancement generative adversarial network to transform acoustic characteristics. Experimental results showed that use of this "enhanced stolen speech" method significantly increases the equal error rates for the baseline used in the ASVspoof 2017 challenge and for a light convolutional neu-ral network-based method. The results also showed that its use degrades the performance of a Gaussian mixture model-universal background model-based ASV system. This type of attack is thus an urgent problem needing to be solved.
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-01889910
Contributor : Md Sahidullah <>
Submitted on : Monday, October 8, 2018 - 10:40:26 AM
Last modification on : Tuesday, September 29, 2020 - 4:14:01 PM
Long-term archiving on: : Wednesday, January 9, 2019 - 1:34:46 PM

File

PID5567621.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01889910, version 1

Collections

Citation

Fuming Fang, Junichi Yamagishi, Isao Echizen, Md Sahidullah, Tomi Kinnunen. Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems. WIFS 2018 - IEEE International Workshop on Information Forensics and Security, Dec 2018, Hong Kong, Hong Kong SAR China. ⟨hal-01889910⟩

Share

Metrics

Record views

182

Files downloads

188