Challenge-based speaker recognition for mobile authentication

Mossab Baloul (1) , Estelle Cherrier (1) , Christophe Rosenberger (1)

1 Equipe SAFE - Laboratoire GREYC - UMR6072

User authentication is a major trend to guarantee the security of electronic transactions when using mobile devices such as tablets or mobile phones. Biometrics is for us the only real user authentication method. In this article, we propose to realize a speaker recognition approach to achieve this goal. We use a challenge-based method to avoid the replay attack (especially if the impostor has recorded the user's voice). In this case, free text recognition is realized. Experimental results on the CMU database show very good results, while providing low computation times.

Domaines: Cryptographie et sécurité [cs.CR]

Mossab Baloul, Estelle Cherrier, Christophe Rosenberger. Challenge-based speaker recognition for mobile authentication. International Conference of the Biometrics Special Interest Group (BIOSIG), 2012, Darmstadt, Germany. 7 p. ⟨hal-00998932⟩