Search

Jason Willia Pelecanos

from White Plains, NY
Age ~48
Get Report
Also known as:
Jason William Pelecanos, Jason W Pelecanos
Phone and address:
631 Knollwood Rd, White Plains, NY 10603
Related to:
Zon E Egwuatu, 65Carolyn D Robinson, 87Olive Egwuatu, 42Glenn Black, 72
Connected to:
Nelson F Pelecas, 42Benjamin L Pelech, 44Cody J Pelech, 67Daria M Pelech, 40Gayland R Pelech, 70Paul Pelech, 49Mara V Pelecis, 53Kristin L Peleckis, 39Dor Peled, 35Einat S Peled, 51

Jason Pelecanos Phones & Addresses

  • 631 Knollwood Rd, White Plains, NY 10603
  • 81 Charter Cir, Ossining, NY 10562 (914) 923-8415
  • 81 Charter Cir APT 3K, Ossining, NY 10562

Publications

Us Patents

Machine And Operating Environment Diagnostics, Detection And Profiling Using Sound

View page
US Patent:
7647827, Jan 19, 2010
Filed:
May 28, 2008
Appl. No.:
12/128321
Inventors:
Jason William Pelecanos - Ossining NY, US
Douglas George Heintzman - Pleasantville NY, US
Jiri Navratil - White Plains NY, US
Ganesh N. Ramaswamy - Mohegan Lake NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G01H 13/00
G01H 17/00
B60C 23/00
US Classification:
73579, 73593, 340442, 340446
Abstract:
A method, system and program storage device are provided for machine diagnostics, detection and profiling using pressure waves, the method including profiling known sources, acquiring pressure wave data, analyzing the acquired pressure wave data, and detecting if the analyzed pressure wave data matches a profiled known source; the system including a processor, a pressure wave transducer in signal communication with the processor, a pressure wave analysis unit in signal communication with the processor, and a source or threat detection unit in signal communication with the processor; and the program storage device including program steps for profiling known sources, acquiring pressure wave data, analyzing the acquired pressure wave data, and detecting if the analyzed pressure wave data matches a profiled known source.

Method And Apparatus For Training A Text Independent Speaker Recognition System Using Speech Data With Text Labels

View page
US Patent:
7813927, Oct 12, 2010
Filed:
Jun 4, 2008
Appl. No.:
12/132770
Inventors:
Jiri Navratil - White Plains NY, US
James H. Nealand - Boambee East, AU
Jason W. Pelecanos - Ossining NY, US
Ganesh N. Ramaswamy - Mohegan Lake NY, US
Ran D. Zilca - Briarcliff Manor NY, US
Assignee:
Nuance Communications, Inc. - Burlington MA
International Classification:
G10L 17/00
G10L 15/00
G10L 15/14
US Classification:
704250, 704246, 704247, 704249, 704256
Abstract:
There is provided an apparatus for providing a Text Independent (TI) speaker recognition mode in a Text Dependent (TD) Hidden Markov Model (HMM) speaker recognition system and/or a Text Constrained (TC) HMM speaker recognition system. The apparatus includes a Gaussian Mixture Model (GMM) generator and a Gaussian weight normalizer. The GMM generator is for creating a GMM by pooling Gaussians from a plurality of HMM states. The Gaussian weight normalizer is for normalizing Gaussian weights with respect to the plurality of HMM states.

Continuous Adaptation In Detection Systems Via Self-Tuning From Target Population Subsets

View page
US Patent:
7970614, Jun 28, 2011
Filed:
May 8, 2007
Appl. No.:
11/745745
Inventors:
Janice J. Kim - White Plains NY, US
Jiri Navratil - Cortlandt Manor NY, US
Jason W. Pelecanos - Ossining NY, US
Ganesh N. Ramaswamy - Mohegan Lake NY, US
Assignee:
Nuance Communications, Inc. - Burlington MA
International Classification:
G10L 15/14
US Classification:
7042562, 704256, 704240, 704248, 704246
Abstract:
The present invention provides a system and method for treating distortion propagated though a detection system. The system includes a compensation module that compensates for untreated distortions propagating through the detection compensation system, a user model pool that comprises of a plurality of model sets, and a model selector that selects at least one model set from plurality of model sets in the user model pool. The compensation is accomplished by continually producing scores distributed according to a prescribed distribution for the at least one model set and mitigating the adverse effects of the scores being distorted and lying off a pre-set operating point. The method for treating distortion propagated though a detection system includes receiving a signal from a remote device, and compensating the signal for untreated distortions. The compensation includes selecting at least one relevant model set from a plurality of model sets, producing scores distributed according to a pre-described distribution for the at least one model set, and mitigating the adverse effect of the scores being distorted by rejecting a signal if it lies off a preset operating point.

Application Of Speech And Speaker Recognition Tools To Fault Detection In Electrical Circuits

View page
US Patent:
8041571, Oct 18, 2011
Filed:
Jan 5, 2007
Appl. No.:
11/620173
Inventors:
Sarah C. McAllister - Ossining NY, US
Tomasz J. Nowicki - Fort Montgomery NY, US
Jason W. Pelecanos - Ossining NY, US
Grzegorz M. Swirszcz - Ossining NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G10L 11/00
G10L 15/16
H02H 3/00
US Classification:
704270, 704232, 361 42
Abstract:
A method and apparatus detect and localize electric faults in electrical power grids and circuit. High impedance faults are detected by analyzing data from remote sensor units deployed over the network using the algorithms of speech and speaker analysis software. This is accomplished by converting the voltage and/or current waveform readouts from the sensors into a digital form which is then transmitted to a computer located either near the sensors or at an operations center. The digitized data is converted by a dedicated software or software/hardware interface to a format accepted by a reliable and stable software solution, such as speech or speaker recognition software. The speech or speaker recognition software must be “trained” to recognize various signal patterns that either indicate or not the occurrence of a fault. The readout of the speech or speaker recognition software, if indicating a fault, is transmitted to a central processor and displayed to provide information on the most likely type of fault. Automatic or human decision is then implemented based on the generated information.

Method And Apparatus For Remote Command, Control And Diagnostics Of Systems Using Conversational Or Audio Interface

View page
US Patent:
8224649, Jul 17, 2012
Filed:
Jun 2, 2004
Appl. No.:
10/858083
Inventors:
Upendra V. Chaudhari - Briarcliff Manor NY, US
Ryan L. Osborn - White Plains NY, US
Jason W. Pelecanos - Ossining NY, US
Ganesh N. Ramaswamy - Ossining NY, US
Ran D. Zilca - Briarcliff Manor NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G10L 11/00
US Classification:
704270, 704246, 704247, 704251, 704252, 704275
Abstract:
A method and apparatus for remote access to a target application is disclosed where a system administrator may establish telephonic contact with an interactive voice response system and obtain access to the target application by speech communication. The interactive response system may authenticate the system administrator by implementing various measures including biometric measures. Once access is granted, the interactive response system may broker a communication between the target application using text/data and the system administrator using natural language.

Speaker Liveness Detection

View page
US Patent:
8589167, Nov 19, 2013
Filed:
May 11, 2011
Appl. No.:
13/105857
Inventors:
Aaron K. Baughman - Silver Spring MD, US
Jason W. Pelecanos - Ossining NY, US
Assignee:
Nuance Communications, Inc. - Burlington MA
International Classification:
G10L 15/02
US Classification:
704270, 704231
Abstract:
A signal representative of an unpredictable audio stimulus is provided to a putative live speaker within a putative live recording environment. A second signal purportedly emanating from the putative live speaker and/or the environment is received. This second signal is examined for influence of the unpredictable audio stimulus on the putative live speaker and/or the putative live recording environment. The examining includes at least one of audio feedback analysis, Lombard analysis, and evoked otoacoustic response analysis. Based on the examining, a determination is made as to whether the putative live speaker is an actual live speaker and/or whether the putative live recording environment is an actual live recording environment.

Method And Apparatus For Determining The Identity Of A User By Narrowing Down From User Groups

View page
US Patent:
20050232470, Oct 20, 2005
Filed:
Mar 31, 2004
Appl. No.:
10/813709
Inventors:
Upendra Chaudhari - Briarcliff Manor NY, US
Jiri Navratil - White Plains NY, US
Jason Pelecanos - Ossining NY, US
Ganesh Ramaswamy - Ossining NY, US
Ran Zilca - Briarcliff Manor NY, US
Assignee:
IBM Corporation - Armonk NY
International Classification:
G06K009/00
US Classification:
382115000
Abstract:
Methods and arrangements for assessing the identity of an individual. Input is accepted from an individual, and at least one user group is attributed to the individual. This attributing is repeated until the identity of the individual is assessed.

Method And Apparatus For Training A Text Independent Speaker Recognition System Using Speech Data With Text Labels

View page
US Patent:
20060111905, May 25, 2006
Filed:
Nov 22, 2004
Appl. No.:
10/994743
Inventors:
Jiri Navratil - White Plains NY, US
James Nealand - Boambee East, AU
Jason Pelecanos - Ossining NY, US
Ganesh Ramaswamy - Mohegan Lake NY, US
Ran Zilca - Briarcliff Manor NY, US
International Classification:
G10L 15/00
US Classification:
704256700
Abstract:
There is provided an apparatus for providing a Text Independent (TI) speaker recognition mode in a Text Dependent (TD) Hidden Markov Model (HMM) speaker recognition system and/or a Text Constrained (TC) HMM speaker recognition system. The apparatus includes a Gaussian Mixture Model (GMM) generator and a Gaussian weight normalizer. The GMM generator is for creating a GMM by pooling Gaussians from a plurality of HMM states. The Gaussian weight normalizer is for normalizing Gaussian weights with respect to the plurality of HMM states.
Control profile
Jason Willia Pelecanos from White Plains, NY, age ~48 Get Report