Low-complexity speech spoofing detection using instantaneous spectral features

Simple item page
dc.contributor.authorSankar, M. S. Arun
dc.contributor.authorDe Leon, Phillip L.
dc.contributor.authorSandoval, Steven
dc.contributor.authorRoedig, Utz
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2022-05-23T13:41:47Z
dc.date.available2022-05-23T13:41:47Z
dc.date.issued2022-05
dc.description.abstractOver the last decade, various detection mechanisms for spoofed speech have been proposed. Thus far the development focus has been on detection accuracy, largely ignoring secondary goals such as computational complexity or storage effort. In this work, we use empirical mode decomposition to compute intrinsic mode functions which are then demodulated to obtain features consisting of short-time statistics of instantaneous amplitude and instantaneous frequency. These features are then used with a simple k-nearest neighbours classifier. We further show that voiced segments from short speech signals can be used in the feature extraction resulting in a spoofing detection competitive with top-performing systems while having up to 103× less computation.en
dc.description.sponsorshipScience Foundation Ireland (19/FFP/6775)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationSankar M. S., A., De Leon, P. L., Sandoval, S. and Roedig, U. (2022) 'Low-complexity speech spoofing detection using instantaneous spectral features,' 2022 29th International Conference on Systems, Signals and Image Processing (IWSSIP), Sofia, Bulgaria, 1-3 June, pp. 1-4. IEEE. Available at https://doi.org/10.1109/IWSSIP55020.2022.9854446en
dc.identifier.doihttps://doi.org/10.1109/IWSSIP55020.2022.9854446
dc.identifier.eissn2157-8702
dc.identifier.endpage4en
dc.identifier.isbn978-1-6654-9578-3
dc.identifier.isbn978-1-6654-9577-6
dc.identifier.isbn978-1-6654-9579-0
dc.identifier.issn2157-8702
dc.identifier.issn2157-8672
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/13215
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.ispartof29th International Conference on Systems, Signals and Image Processing (IWSSIP 2022), Sofia, Bulgaria, 1-3 June, 2022, hosted by the Technical University of Sofia.
dc.relation.urihttp://iwssip.bg/
dc.rights© 2022, the Authors. For the purpose of Open Access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. Published version © 2022 IEEEen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectComputer securityen
dc.subjectBiometricsen
dc.subjectSpeaker recognitionen
dc.subjectSpeech processingen
dc.titleLow-complexity speech spoofing detection using instantaneous spectral featuresen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SpoofdetectionEMD.pdf
Size:
314.35 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items