System and method for authentication using speaker verification techniques and fraud model

作者: John F. Sheets , Kim R. Wagner

DOI:

关键词: Communication deviceProcess (computing)Speaker verificationSample (statistics)AuthenticationString (computer science)Voice TagComputer scienceSpeech recognitionWord (computer architecture)

摘要: Embodiments of the invention provide for speaker verification on a communication device without requiring user to go through formal registration process with issuer or network. Certain embodiments allow use captured voice sample attempting reproduce word string having random element authenticate user. Authentication is based both match score indicating how closely samples previously stored and pass fail response whether an accurate reproduction string. The processing network maintains history authenticated transactions samples.

参考文章(54)
Yuk L. Li, Padmaja Ramadas, Biometric authentication based upon usage history ,(2009)
Amanda Stent, Jay Wilpon, Ann K. Syrdal, Ilija Zeljkovic, Taniya Mishra, System and method for generating challenge utterances for speaker verification ,(2010)
Vivek Borkar, Nagaraj M. Hunur, Swati Jain, Ashton Kawanishi, Rakesh Gajula, Vinayaka Vasanth Prabhu, Balamurali Krishna Manyam, Adam Gates, Vikas Kumar, Method, system, and graphical user interface for presenting an interactive hierarchy and indicating entry of information therein ,(2008)
Sandra A. Johanesen, Cynthia Zhu, Ryan J. Verhey-Henke, Michael Ward, Medical biometric identification security system ,(2005)
Blayn Beenau, David Bonalle, Peter Saunders, Joshua Montgomery, William Gray, Seth Fields, Carl Larkin, Method and system for voice recognition biometrics on a fob ,(2004)