Yogen Patel resumes & CV records
Resumes
Yogen Patel
Yogen Patel
Product Management And Marketing Executive
Location:
San Francisco Bay Area
Industry:
Computer Software
Yogen Navinbhai Patel, Age 57603 Romeo Ct, Pleasanton, CA 94566
Yogen Patel Phones & Addresses
603 Romeo Ct, Pleasanton, CA 94566 (925) 822-6068
45745 Cayuga Ct, Fremont, CA 94539 (510) 659-1989
1775 Milmont Dr, Milpitas, CA 95035 (408) 262-1110
Waltham, MA
Santa Clara, CA
Philadelphia, PA
Boston, MA
Overland Park, KS
Alameda, CA
603 Romeo Ct, Pleasanton, CA 94566
Work
Position:
Professional/Technical
Mentions for Yogen Navinbhai Patel
Publications & IP owners
Us Patents
Multi-Dialect Speech Recognition Method And Apparatus
US Patent:
5865626, Feb 2, 1999
Filed:
Aug 30, 1996
Appl. No.:
8/705742
Inventors:
Valerie L. Beattie - Burlington MA
David R. H. Miller - Cambridge MA
Shawn Eric Edmondson - Indianapolis IN
Yogen N. Patel - Philadelphia PA
Geoffrey A. Talvola - Somerville MA
David R. H. Miller - Cambridge MA
Shawn Eric Edmondson - Indianapolis IN
Yogen N. Patel - Philadelphia PA
Geoffrey A. Talvola - Somerville MA
Assignee:
GTE Internetworking Incorporated - Cambridge MA
International Classification:
G09B 1904
US Classification:
434185
Abstract:
Apparatus and method for improving the speed an accuracy of recognition of speech dialects, or speech tansferred via dissimilar channels is described. The invention provides multiple models tailored to specific segments or dialects, and/or speech channels, of the population. However, there is not a proportional increase in recognition time or computing power or computing resources needed. Probability density functions for the acoustic descriptors are provided which are shared among the various models. Since there is a common pool of probability density functions which are mapped or pointed to for the different acoustic descriptors for each different dialect or speech channel model, the memory requirements for the speech recognition apparatus and method are significantly reduced. Each model is comprised of triphonemes which are modelled by discrete probability distribution functions forming hidden Markov models or statistical word models. Any one probability density function is assigned or mapped to many different triphonemes in many different dialects or different models.
Possible Relatives
NOTICE: You may not use PeopleBackgroundCheck or the information it provides to make decisions about employment, credit, housing or any other purpose that would require Fair Credit Reporting Act (FCRA) compliance. PeopleBackgroundCheck is not a Consumer Reporting Agency (CRA) as defined by the FCRA and does not provide consumer reports.