Rutgers, the State University of New Jersey

Kevin Farrell

Richard James Mammone

Manish Sharma

Xiaoyu Zhang

Han-Seng Liou

Khaled Assaleh

Brian Freeman

Devang Naik

The present invention relates to a pattern recognition system which uses data fusion to combine data from a plurality of extracted features and a plurality of classifiers. Speaker patterns can be accurately verified with the combination of discriminant based and distortion based classifiers. A novel approach using a training set of a 'leave one out' data can be used for training the system with a reduced data set. Extracted features can be improved with a pole filtered method for reducing channel effects and an affine transformation for improving the correlation between training and testing data.

Speaker verification system using decision fusion logic

A method and apparatus for improved mobile radio telecommunications employs the transmission of a pilot reference signal within the coherence band of the modulated carrier wave. The receiver in this system uses instantaneous phase estimation techniques of the pilot and carrier received waveforms to provide immunity from phase distortion introduced by the channel.

Fixed reference shift keying modulation for mobile radio

Growing community of inventors

MIlford, CT, United States of America

Kevin Farrell