Telecommunication device having fraud prevention features

作者: Assaleh Khaled , Campbell William Michael

DOI:

关键词: Pattern recognitionFeature vectorArtificial intelligenceClassifier (UML)Computer science

摘要: A TCS (200) and procedure (400) for identifying an unidentified class as a of group classes includes new tree-structured classifier (208) training processor (204). Unidentified feature vectors representing are combined with predetermined models to compute score each the vectors. Based on scores vectors, association is made identify class. Predetermined created using (300) associated therewith. useful when determining access privileges device or system.

参考文章(33)
Khaled Talal Assaleh, William Michael Campbell, Method and apparatus for training a speaker recognition system ,(1997)
Mukund Padmanabhan, David Nahamoo, Lalit Rai Bahl, Peter Vincent deSouza, System and method for partitioning the feature space of a classifier in a pattern classification system ,(1997)
Khaled Assaleh, Devang Naik, Manish Sharma, Han-Seng Liou, Richard J. Mammone, Xiaoyu Zhang, Kevin Farrell, Speaker verification system using decision fusion logic ,(1995)
Luigi Stringa, Tomaso A. Poggio, Daniele Falavigna, Roberto Brunelli, Recognition system, particularly for recognising people ,(1993)
K.R. Farrell, R.P. Ramachandran, M. Sharma, R.J. Mammone, Sub-word speaker verification using data fusion methods Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop. pp. 531- 540 ,(1997) , 10.1109/NNSP.1997.622435
K.R. Farrell, Text-dependent speaker verification using data fusion international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 349- 352 ,(1995) , 10.1109/ICASSP.1995.479545
Michael Jack Newman, Laurence S. Gillick, Yoshiko Ito, Speaker identification using unsupervised speech models ,(1997)
Shay-Ping Thomas Wang, Artificial neuron and method of using same ,(1994)