Systems, methods, and media for determining fraud risk from audio signals

作者: Torsten Zeppenfeld , Lisa Guerra , Vipul Vyas , Anthony Rajakumar

DOI:

关键词: Event (computing)Channel modelsSpeech recognitionPath (computing)Communication channelComputer scienceIdentifierAudio signalServer system

摘要: Systems, methods, and media for determining fraud risk from audio signals non-audio data are provided herein. Some exemplary methods include receiving an signal associated identifier, a event identifier with event, speaker model based on the received signal, channel path of using server system, updating fraudster database to determined comparison identified, voice identifier.

参考文章(6)
Vicki Broman, Speaker recognition in a multi-speaker environment and comparison of several voice prints to many Journal of the Acoustical Society of America. ,vol. 131, pp. 4867- ,(2004) , 10.1121/1.4728396
Oren Pereg, Moshe Wasserblat, Ilan Kor, Barak Eilam, Method and apparatus for fraud detection ,(2006)
Eli Talmor, Rita Talmor, Alon Talmor, Voice authentication method and system utilizing same ,(2000)