Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Analysing the predictions of a CNN-based replay spoofing detection system
Queen Mary Univ London, Sch EECS, London, England..
Queen Mary Univ London, Sch EECS, London, England..
KTH, School of Electrical Engineering and Computer Science (EECS), Speech, Music and Hearing, TMH. Queen Mary Univ London, Sch EECS, London, England..
2018 (English)In: 2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), IEEE , 2018, p. 92-97Conference paper, Published paper (Refereed)
Abstract [en]

Playing recorded speech samples of an enrolled speaker – “replay attack” – is a simple approach to bypass an automatic speaker ver- ification (ASV) system. The vulnerability of ASV systems to such attacks has been acknowledged and studied, but there has been no research into what spoofing detection systems are actually learning to discriminate. In this paper, we analyse the local behaviour of a replay spoofing detection system based on convolutional neural net- works (CNNs) adapted from a state-of-the-art CNN (LC N NF F T ) submitted at the ASVspoof 2017 challenge. We generate tempo- ral and spectral explanations for predictions of the model using the SLIME algorithm. Our findings suggest that in most instances of spoofing the model is using information in the first 400 milliseconds of each audio instance to make the class prediction. Knowledge of the characteristics that spoofing detection systems are exploiting can help build less vulnerable ASV systems, other spoofing detection systems, as well as better evaluation databases.

Place, publisher, year, edition, pages
IEEE , 2018. p. 92-97
Series
IEEE Workshop Spoken Lang. Tech.
Keywords [en]
Automatic speaker verification, spoofing detection, replay attack, spoofing countermeasure
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-248981ISI: 000463141800014Scopus ID: 2-s2.0-85063092177ISBN: 978-1-5386-4334-1 (print)OAI: oai:DiVA.org:kth-248981DiVA, id: diva2:1303666
Conference
2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018)
Note

QC 20190423

Available from: 2019-04-10 Created: 2019-04-10 Last updated: 2019-08-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

Scopus

Authority records BETA

Sturm, Bob

Search in DiVA

By author/editor
Sturm, Bob
By organisation
Speech, Music and Hearing, TMH
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 106 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf