System and Method for Multi-Modal Audio Mining of Telephone Conversations

作者: Andreas M. Olligschlaeger , James P. Rokosky

DOI:

关键词:

摘要: A system and method for the automated monitoring of inmate telephone calls as well multi-modal search, retrieval playback capabilities said calls. general term such is audio mining. The invention designed to provide an efficient means organizations correctional facilities identify monitor contents conversations evidence possible inappropriate conduct and/or criminal activity inmates by analyzing monitored events, including, but not limited to, addition third parties, discussion particular topics, mention certain entities.

参考文章(317)
Upendra V. Chaudhari, Stéphane H. Maes, Jií Navrátil, A Speech Biometrics System with Multi- Grained Speaker Modeling sprachkommunikation. pp. 237- 242 ,(2000)
Ric Simmons, Why 2007 is Not Like 1984: A Broader Perspective on Technology's Effect on Privacy and Fourth Amendment Jurisprudence Journal of Criminal Law & Criminology. ,vol. 97, pp. 531- 568 ,(2007)
Raquel Tato, Thomas Kemp, Krzysztof Marasek, Method for speaker identification ,(2001)
Charles Dye, Oracle Distributed Systems ,(1999)
Upendra V. Chaudhari, Jirí Navrátil, Stéphane H. Maes, Ramesh A. Gopinath, Transformation enhanced multi-grained modeling for text-independent speaker recognition. conference of the international speech communication association. pp. 298- 301 ,(2000)