Speaker verification system using decision fusion logic

Details Speaker verification system using decision fusion logic Speaker verification system using decision fusion logic

1995-06-07

1998-11-17

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704231, 704234, 704270, G10L 500

Patent

active

058391037

ABSTRACT:
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.

REFERENCES:
patent: 4837831 (1989-06-01), Gillick et al.
patent: 4975961 (1990-12-01), Sakoe
patent: 5220640 (1993-06-01), Frank
patent: 5271088 (1993-12-01), Bahler
patent: 5404422 (1995-04-01), Sakamoto et al.
patent: 5410635 (1995-04-01), Sakoe
patent: 5430827 (1995-07-01), Rissanen
patent: 5457770 (1995-10-01), Miyazawa
patent: 5522012 (1996-05-01), Mammone et al.
patent: 5528728 (1996-06-01), Mastsuura et al.
Farrell, Mammone, and Assaleh, "Speaker Recognition Using Neural Networks and Conventional Classifiers," IEEE Trans. on Speech and Audio Processing, v. 2, n. 1, p. 11, pp. 194-205, Jan. 1994.
Deller, Proakis, and Hansen, "Discrete-Time Processing of Speech Signals," 1987, pp. 115-117.
Assaleh and Mammone, "Robust Cepstral Features for Speaker Identification," ICASSP-94, Apr. 19-22, 1994, pp. 129-132.
Farrell, "Text-Dependent Speaker Verification Using Data Fusion," ICASSP-95, May 9-12, 1995, pp. 349-352.
Farrell and Mammone, "Modulation Classification Using a Neural Tree Network," MILCOM-93, Oct. 11-14, 1993, pp. 1028-1032.
Sankar and Mammone, "Growing and Pruning Neural Tree Networks," IEEE Trans. on Computers, 42(3):291-99, Mar. 1993.
Sankar and Mammone, "Speaker Independent Vowel Recognition Using Neural Tree Networks," IJCNN-91, Jul. 8-14, 1991, pp. 809-814.
Farrell and Mammone, "Speaker Identification Using Neural Tree Networks," ICASSP-94, Apr. 19-22, 1994, pp. 165-168.
Sharma and Mammone, "Speech Recognition Using Sub-Word Neural Tree Network Models and Multiple Classifier Fusion," ICASSP-95, May 9-12, 1995, pp. 3323-3326.
Liou and Mammone, "A Subword Neural Tree Network Approach to Text-Dependent Speaker Verification," May 9-12, 1995, pp. 357-360.
Assaleh and Mammone, "New LP-Derived Features for Speaker Identification," IEEE Trans. on Speech and Audio Processing, 2(4):630-638, Oct. 1994.
Farrell, Mammone, and Gorin, "Adaptive Language Acquisition Using Incremental Learning," ICASSP-93, Apr. 27-30, 1993, pp. 501-504.

Affiliated with

Also associated with

Rating

Speaker verification system using decision fusion logic does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speaker verification system using decision fusion logic, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker verification system using decision fusion logic will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-896964