Methods and apparatus for statistical biometric model migration

Details Methods and apparatus for statistical biometric model migration Methods and apparatus for statistical biometric model migration

2004-05-28

2009-02-24

Edouard, Patrick N (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S256200, C704S244000

Reexamination Certificate

active

07496509

ABSTRACT:
In large-scale deployments of speaker recognition systems the potential for legacy problems increases as the evolving technology may require configuration changes in the system thus invalidating already existing user voice accounts. Unless the entire database of original speech waveform were stored, users need to reenroll to keep their accounts functional, which, however, may be expensive and commercially not acceptable. Model migration is defined as a conversion of obsolete models to new-configuration models without additional data and waveform requirements. The present disclosure investigates ways to achieve such a migration with minimum loss of system accuracy.

REFERENCES:
patent: 5185848 (1993-02-01), Aritsuka et al.
patent: 5793891 (1998-08-01), Takahashi et al.
patent: 5893059 (1999-04-01), Raman
patent: 6151575 (2000-11-01), Newman et al.
patent: 6167377 (2000-12-01), Gillick et al.
patent: 6343267 (2002-01-01), Kuhn et al.
patent: 6529871 (2003-03-01), Kanevsky et al.
patent: 7072834 (2006-07-01), Zhou
patent: 2004/0122672 (2004-06-01), Bonastre et al.
“NIST—Speaker Recognition Evaluations” retrieved Jan. 9, 2006 from http://www.nist.gov/speech/tests/spk/index.htm.
S.H. Maes, J. Navratil, U.V. Chaudhari, “Conversational speech biometrics”, chapter in “Advances in E-commerce Agents: Broking, Negotiation, Security, and Mobility,” Lecture Notes in Artificial Intelligence, Springer 2000.
U.V. Chaudhari, J. Navratil, G.N. Ramaswamy, R.D. Zilca “Future speaker recognition systems: Challenges and solutions,” Proc. of AUTOID-2002, Tarrytown, NY, Mar. 2002.
G. Ramaswamy, J. Navratil, U. Chaudhari, and R. Zilca, “The IBM system for the NIST 2002 cellular speaker verification evaluation,” in Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), (Hong Kong), IEEE, Apr. 2003.
U.V. Chaudhari, J. Navr'atil, and S.H. Maes. Multigrained modeling with pattern-specific maximum likelihood transformations for text-independent speaker recognition. IEEE Trans. Speech and Audio Processing, 2002.
D. Reynolds, T. Quatieri, and R. Dunn. Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10(1-3):19-41, 2000.
R.O. Duda et al., “Pattern Classification,” John Wiley & Sons, 2nd Ed., pp. 282-284, 2001.
D. Chazan, G. Cohen, R. Hoory, M. Zibulski, “Speech reconstruction from mel-frequency cepstral co-efficients and pitch frequency,” in Proc. Of the International Conference on Acoustics, Speech and Signal processing (ICASSP), Jun. 2000.
J. Navratil, Ganesh Ramaswamy, Ran Zilca, “Statistical Model Migration in Speaker Recognition”, IBM T.J. Watson Research Center.

Affiliated with

Also associated with

Rating

Methods and apparatus for statistical biometric model migration does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Methods and apparatus for statistical biometric model migration, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods and apparatus for statistical biometric model migration will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4114396