Inventors list

Assignees list

Classification tree browser

Top 100 Inventors

Top 100 Assignees


David Nahamoo

David Nahamoo, White Plains, NY US

Patent application numberDescriptionPublished
20080312921SPEECH RECOGNITION UTILIZING MULTITUDE OF SPEECH FEATURES - In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.12-18-2008
20090313026CONVERSATIONAL COMPUTING VIA CONVERSATIONAL VIRTUAL MACHINE - A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) 12-17-2009

Patent applications by David Nahamoo, White Plains, NY US

David Nahamoo, Great Neck, NY US

Patent application numberDescriptionPublished
20090254496SYSTEM AND METHOD FOR OPTIMIZING PATTERN RECOGNITION OF NON-GAUSSIAN PARAMETERS - A method of optimizing a function of a parameter includes associating, with an objective function for initial value of parameters, an auxiliary function of parameters that could be optimized computationally more efficiently than an original objective function, obtaining parameters that are optimum for the auxiliary function, obtaining updated parameters by taking a weighted sum of the optimum of the auxiliary function and initial model parameters.10-08-2009
20090259471DISTANCE METRICS FOR UNIVERSAL PATTERN PROCESSING TASKS - A universal pattern processing system receives input data and produces output patterns that are best associated with said data. The system uses input means receiving and processing input data, a universal pattern decoder means transforming models using the input data and associating output patterns with original models that are changed least during transforming, and output means outputting best associated patterns chosen by a pattern decoder means.10-15-2009
20090276539Conversational Asyncronous Multichannel Communication through an Inter-Modality Bridge - A communications apparatus is configured to bridge modalities and different communications formats. The apparatus may include a bridge to receive an input through a modality gateway and to deliver an output through an output channel, a communication engine configured to manipulate the input into the output, a router configured to route the configured output to a respective output channel, and a controller configured to control the bridge. The controller may determine a new modality depending on a context of the communications apparatus.11-05-2009
20110282925DIRECTIONAL OPTIMIZATION VIA EBW - An optimization system and method includes determining a best gradient as a sparse direction in a function having a plurality of parameters. The sparse direction includes a direction that maximizes change of the function. This maximum change of the function is determined by performing an optimization process that gives maximum growth subject to a sparsity regularized constraint. An extended Baum Welch (EBW) method can be used to identify the sparse direction. A best step size is determined along the sparse direction by finding magnitudes of entries of direction that maximizes the function restricted to the sparse direction. A solution is recursively refined for the function optimization using a processor and storage media.11-17-2011
20110304446SYSTEM FOR PREVENTING HANDHELD DEVICE USE WHILE OPERATING A VEHICLE - Techniques for preventing a driver of a moving vehicle from using a handheld device while driving. An example system of the invention includes a plurality of biometric sensors configured to receive biometric data from the driver and a user of the handheld device. Contemporaneously with operation of the vehicle and the handheld device, the biometric data is analyzed in order to determine a match between the identity of the vehicle driver and the user of the handheld device. A controller is configured to selectively interrupt operation of the vehicle or handheld device upon detecting the match.12-15-2011
20120016674Modification of Speech Quality in Conversations Over Voice Channels - Techniques are disclosed for modifying speech quality in a conversation over a voice channel. For example, a method for modifying a speech quality associated with a spoken utterance transmittable over a voice channel comprises the following steps. The spoken utterance is obtained prior to an intended recipient of the spoken utterance receiving the spoken utterance. An existing speech quality of the spoken utterance is determined. The existing speech quality of the spoken utterance is compared to at least one desired speech quality associated with at least one previously obtained spoken utterance to determine whether the existing speech quality substantially matches the desired speech quality. At least one characteristic of the spoken utterance is modified to change the existing speech quality of the spoken utterance to the desired speech quality when the existing speech quality does not substantially match the desired speech quality. The spoken utterance is presented with the desired speech quality to the intended recipient.01-19-2012

Patent applications by David Nahamoo, Great Neck, NY US