Voice-Quality Features for Replay Attack Detection

Abraham Zewoudie, Tom Bäckström

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

4 Sitaatiot (Scopus)
118 Lataukset (Pure)

Abstrakti

Replay 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.
AlkuperäiskieliEnglanti
Otsikko2022 30th European Signal Processing Conference (EUSIPCO)
KustantajaIEEE
Sivut384-388
Sivumäärä5
ISBN (elektroninen)978-90-827970-9-1
ISBN (painettu)978-1-6654-6799-5
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaEuropean Signal Processing Conference - Belgrade, Serbia
Kesto: 29 elok. 20222 syysk. 2022
Konferenssinumero: 30
https://2022.eusipco.org/

Julkaisusarja

NimiEuropean Signal Processing Conference
ISSN (painettu)2219-5491
ISSN (elektroninen)2076-1465

Conference

ConferenceEuropean Signal Processing Conference
LyhennettäEUSIPCO
Maa/AlueSerbia
KaupunkiBelgrade
Ajanjakso29/08/202202/09/2022
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Voice-Quality Features for Replay Attack Detection'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä