new TOP 200 Companies filing patents this week

new Companies with the Most Patent Filings

Tara N. Sainath patents

Recent patents with Tara N. Sainath listed as an inventor - additional entries may be under other spellings.


Tara N. Sainath - Related organizations: Google Inc. patents, International Business Machines Corporation patents

User specified keyword spotting using long short term memory neural network feature extractor

03/16/17 - 20170076717 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing keywords using a long short term memory neural network. One of the methods includes receiving, by a device for each of multiple variable length enrollment audio signals, a respective plurality of enrollment feature vectors that represent
Inventors: Maria Carolina Parada San Martin, Tara N. Sainath, Guoguo Chen

Compressed recurrent neural network models

03/16/17 - 20170076196 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing long-short term memory layers with compressed gating functions. One of the systems includes a first long short-term memory (LSTM) layer, wherein the first LSTM layer is configured to, for each of the plurality of time steps,
Inventors: Tara N. Sainath, Vikas Sindhwani

Reducing cognitive demand on a vehicle operator by generating passenger stimulus

02/16/17 - 20170043782 - A method for reducing cognitive demand on a vehicle operator comprises detecting one or more passengers in a vehicle in addition to the vehicle operator, determining an acceptable level of cognitive demand on the vehicle operator corresponding to an operating environment, determining an existing level of cognitive demand on the
Inventors: Robert G. Farrell, Dimitri Kanevsky, Tara N. Sainath

Processing multi-channel audio waveforms

11/03/16 - 20160322055 - Methods, including computer programs encoded on a computer storage medium, for enhancing the processing of audio waveforms for speech recognition using various neural network processing techniques. In one aspect, a method includes: receiving multiple channels of audio data corresponding to an utterance; convolving each of multiple filters, in a time
Inventors: Tara N. Sainath, Ron J. Weiss, Kevin William Wilson, Andrew W. Senior, Arun Narayanan, Yedid Hoshen, Michiel A.u. Bacchiani

Speaker recognition using neural networks

10/06/16 - 20160293167 - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing speaker verification. In one aspect, a method includes accessing a neural network having an input layer that provides inputs to a first hidden layer whose nodes are respectively connected to only a proper subset of
Inventors: Yu-hsin Joyce Chen, Ignacio Lopez Moreno, Tara N. Sainath, Maria Carolina Parada San Martin

Processing audio waveforms

09/29/16 - 20160284347 - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural
Inventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson

Convolutional neural networks

09/29/16 - 20160283841 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for keyword spotting. One of the methods includes training, by a keyword detection system, a convolutional neural network for keyword detection by providing a two-dimensional set of input values to the convolutional neural network, the input values including
Inventors: Tara N. Sainath, Maria Carolina Parada San Martin

User specified keyword spotting using long short term memory neural network feature extractor

06/23/16 - 20160180838 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing keywords using a long short term memory neural network. One of the methods includes receiving, by a device for each of multiple variable length enrollment audio signals, a respective plurality of enrollment feature vectors that represent
Inventors: Maria Carolina Parada San Martin, Tara N. Sainath, Guoguo Chen

Convolutional, long short-term memory, fully connected deep neural networks

04/07/16 - 20160099010 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying the language of a spoken utterance. One of the methods includes receiving input features of an utterance; and processing the input features using an acoustic model that comprises one or more convolutional neural network (CNN) layers,
Inventors: Tara N. Sainath, Andrew W. Senior, Oriol Vinyals, Hasim Sak

Low-rank hidden input layer for speech recognition neural network

03/31/16 - 20160092766 - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods for training a deep neural network that includes a low rank hidden input layer and an adjoining hidden layer, the low rank hidden input layer including a first
Inventors: Tara N. Sainath, Maria Carolina Parada San Martin

System and method for generating content corresponding to an event

03/17/16 - 20160078119 - Systems and methods for generating content corresponding to an event are provided. A method for generating content corresponding to an event, comprises defining a plurality of sub-events of the event, classifying one or more actual occurrences in the event into one or more of the sub-events, monitoring behavior of one
Inventors: Aleksandr Y. Aravkin, Carlos H. Cardonha, Sasha P. Caskey, Dimitri Kanevsky, Tara N. Sainath

System and method for feeling surface roughness through microscopic data

02/18/16 - 20160048997 - Systems and methods for generating a tactile representation of an object are provided. A method for generating a tactile representation of an object, comprises obtaining a microscopic image of a surface of the object, processing data corresponding to the image to generate a roughness pattern for the object based on
Inventors: Aleksandr Y. Aravkin, Anirban Basu, Dimitri Kanevsky, Tara N. Sainath

System and method for using biometrics to predict and select music preferences

12/17/15 - 20150363491 - Systems and methods for using biometrics to select music preference are provided. A system for using biometrics to select music preferences for a user in a vehicle, comprises a music selection module electrically coupled to at least one biometric sensor in the vehicle, wherein the at least one biometric sensor
Inventors: Sasha P. Caskey, Dimitri Kanevsky, Sameer R. Maskey, Tara N. Sainath

System and method for using biometrics to predict and select music preferences

12/17/15 - 20150363164 - Systems and methods for using biometrics to select music preference are provided. A system for using biometrics to select music preferences for a user in a vehicle, comprises a music selection module electrically coupled to at least one biometric sensor in the vehicle, wherein the at least one biometric sensor
Inventors: Sasha P. Caskey, Dimitri Kanevsky, Sameer R. Maskey, Tara N. Sainath

Systems and methods for applying speaker adaption techniques to correlated features

06/11/15 - 20150161993 - Systems and methods for applying feature-space maximum likelihood linear regression (fMLLR) to correlated features are provided. A method for applying fMLLR to correlated features, comprises mapping the correlated features into an uncorrelated feature space, applying fMLLR in the uncorrelated feature space to obtain fMLLR transformed features, and mapping the fMLLR
Inventors: Tara N. Sainath, George A. Saon

Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling

06/11/15 - 20150161987 - A method for training a deep neural network, comprises receiving and formatting speech data for the training, preconditioning a system of equations to be used for analyzing the speech data in connection with the training by using a non-fixed point quasi-Newton preconditioning scheme, and employing flexible Krylov subspace solvers in
Inventors: Lior Horesh, Brian E.d. Kingsbury, Tara N. Sainath


### Tara N. Sainath patent invention listings

The bibliographic references displayed about Tara N. Sainath's patents are for a recent sample of Tara N. Sainath's publicly published patent applications. The inventor/author may have additional bibliographic citations listed at the USPTO.gov. FreshPatents.com is not associated or affiliated in any way with the author/inventor or the United States Patent/Trademark Office but is providing this non-comprehensive sample listing for educational and research purposes using public bibliographic data published and disseminated from the United States Patent/Trademark Office public datafeed. This information is also available for free on the USPTO.gov website. If Tara N. Sainath filed recent patent applications under another name, spelling or location then those applications could be listed on an alternate page. If no bibliographic references are listed here, it is possible there are no recent filings or there is a technical issue with the listing--in that case, we recommend doing a search on the USPTO.gov website.

###



Sign up for the FreshPatents.com FREE Keyword Monitor and check for keyword phrases (ie. "RFID" , "wireless", "web development", "fuel cells" etc.)...You will be notified when new patent applications and inventions are published that match your keywords. Also you can save for later research public patent/invention documents using our FREE Organizer. It takes only 30 seconds to sign up or login.

Advertise on FreshPatents.com - Rates & Info

###

FreshPatents.com Support - Terms & Conditions