Voice-Quality Features for Replay Attack Detection

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorZewoudie, Abrahamen_US
dc.contributor.authorBäckström, Tomen_US
dc.contributor.departmentDept Signal Process and Acousten_US
dc.contributor.departmentSpeech Interaction Technologyen_US
dc.date.accessioned2022-11-23T08:01:14Z
dc.date.available2022-11-23T08:01:14Z
dc.date.issued2022en_US
dc.description.abstractReplay attacks are attempts to get fraudulent access to an automatic speaker verification system. In this paper, we investigate the usefulness of voice quality features to detect replay attacks. The voice quality features are used together with the state-of-the-art constant Q cepstral coefficients (CQCC) features. The two feature sets are fused at the score level. Thus, the log-likelihood scores estimated from the two feature sets are linearly weighted to obtain a single fused score. The fused score is used to classify whether a given speech sample is genuine or spoofed. Our experiments with the ASVspoof 2017 dataset demonstrate that the fusion of log-likelihood scores extracted from the CQCC and voice quality features improve the Equal Error Rate (EER) compared to the baseline system which is based only on CQCC features.en
dc.description.versionPeer revieweden
dc.format.extent5
dc.format.extent384-388
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationZewoudie , A & Bäckström , T 2022 , Voice-Quality Features for Replay Attack Detection . in 2022 30th European Signal Processing Conference (EUSIPCO) . European Signal Processing Conference , IEEE , pp. 384-388 , European Signal Processing Conference , Belgrade , Serbia , 29/08/2022 . < https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9909802 >en
dc.identifier.isbn978-1-6654-6799-5
dc.identifier.isbn978-90-827970-9-1
dc.identifier.issn2219-5491
dc.identifier.issn2076-1465
dc.identifier.otherPURE UUID: 790b6edf-6d5a-4bf2-947c-1f7c205bc23ben_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/790b6edf-6d5a-4bf2-947c-1f7c205bc23ben_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85141011627&partnerID=8YFLogxKen_US
dc.identifier.otherPURE LINK: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9909802en_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/86044571/Voice_Quality_Features_for_Replay_Attack_Detection.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/117832
dc.identifier.urnURN:NBN:fi:aalto-202211236592
dc.language.isoenen
dc.relation.ispartofEuropean Signal Processing Conferenceen
dc.relation.ispartofseries2022 30th European Signal Processing Conference (EUSIPCO)en
dc.relation.ispartofseriesEuropean Signal Processing Conferenceen
dc.rightsopenAccessen
dc.titleVoice-Quality Features for Replay Attack Detectionen
dc.typeConference article in proceedingsfi
dc.type.versionacceptedVersion
Files