Can spoofing countermeasure and speaker verification systems be jointly optimised? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Can spoofing countermeasure and speaker verification systems be jointly optimised?

Résumé

Spoofing countermeasure (CM) and automatic speaker verification (ASV) sub-systems can be used in tandem with a backend classifier as a solution to the spoofing aware speaker verification (SASV) task. The two sub-systems are typically trained independently to solve different tasks. While our previous work demonstrated the potential of joint optimisation, it also showed a tendency to over-fit to speakers and a lack of sub-system complementarity. Using only a modest quantity of auxiliary data collected from new speakers, we show that joint optimisation degrades the performance of separate CM and ASV sub-systems, but that it nonetheless improves complementarity, thereby delivering superior SASV performance. Using standard SASV evaluation data and protocols, joint optimisation reduces the equal error rate by 27\% relative to performance obtained using fixed, independently-optimised sub-systems under like-for-like training conditions.

Dates et versions

hal-04031754 , version 1 (16-03-2023)

Identifiants

Citer

Wanying Ge, Hemlata Tak, Massimiliano Todisco, Nicholas Evans. Can spoofing countermeasure and speaker verification systems be jointly optimised?. ICASSP 2023, IEEE International Conference on Acoustics, Speech and Signal Processing, 4-10 June 2023, Rhodes Islands, Greece, Jun 2023, Rhodes Islands, Greece. ⟨hal-04031754⟩

Collections

EURECOM ANR
28 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More