Challenge-based speaker recognition for mobile authentication
Year: 2012
Type: article
Abstract: : 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. 1
Authors: M. Baloul, E. Cherrier, C. Rosenberger
Institutions: GREYC, Université de Caen Normandie
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1559450307