Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2006-08-25
2010-02-16
Vo, Huyen X. (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S243000, C704S256200, C704S256400
Reexamination Certificate
active
07664643
ABSTRACT:
A method, and a system to execute this method is being presented for the identification and separation of sources of an acoustic signal, which signal contains a mixture of multiple simultaneous component signals. The method represents the signal with multiple discrete state-variable sequences and combines acoustic and context level dynamics to achieve the source separation. The method identifies sources by discovering those frames of the signal whose features are dominated by single sources. The signal may be the simultaneous speech of multiple speakers.
REFERENCES:
patent: 6950796 (2005-09-01), Ma
patent: 6963835 (2005-11-01), Kimball
patent: 7062433 (2006-06-01), Gong
patent: 7107210 (2006-09-01), Deng
patent: 7146319 (2006-12-01), Hunt
patent: 7467086 (2008-12-01), Menendez-Pidal et al.
patent: 2006/0206333 (2006-09-01), Paek
patent: 2006/0229875 (2006-10-01), Acero
P. Varga and R.K. Moore, “Hidden markov model decomposition of speech and noise” ICASSP, pp. 845-848, 1990.
Gopinath Ramesh Ambat
Hershey John Randall
Kristjansson Trausti Thor
Olsen Peder Andreas
Rennie Steven John
International Business Machines - Corporation
Nuance Communications Inc.
Vo Huyen X.
Wolf Greenfield & Sacks P.C.
LandOfFree
System and method for speech separation and multi-talker... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for speech separation and multi-talker..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for speech separation and multi-talker... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4225665