Patents by Inventor Tushar Agarwal

Tushar Agarwal has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250046323
    Abstract: A device includes a neural network and a sample generator. The neural network is configured to process one or more neural network inputs to generate a joint probability distribution. The one or more neural network inputs include at least first previous sample data and second previous sample data associated with at least one previous data sample of a sequence of data samples. The sample generator is configured to generate first sample data and second sample data based on the joint probability distribution. The first sample data and the second sample data are associated with at least one data sample of the sequence of data samples.
    Type: Application
    Filed: November 16, 2022
    Publication date: February 6, 2025
    Inventors: Zisis Iason SKORDILIS, Vivek RAJENDRAN, Tushar AGARWAL
  • Patent number: 12159618
    Abstract: An example method of automated selection of audio asset synthesizing pipelines includes: receiving an audio stream comprising human speech; determining one or more features of the audio stream; selecting, based on the one or more features of the audio stream, an audio asset synthesizing pipeline; training, using the audio stream, one or more audio asset synthesizing models implementing respective stages of the selected audio asset synthesizing pipeline; and responsive to determining that a quality metric of the audio asset synthesizing pipeline satisfies a predetermined quality condition, synthesizing one or more audio assets by the selected audio asset synthesizing pipeline.
    Type: Grant
    Filed: October 20, 2022
    Date of Patent: December 3, 2024
    Assignee: Electronic Arts Inc.
    Inventors: Kilol Gupta, Tushar Agarwal, Zahra Shakeri, Mohsen Sardari, Harold Henry Chaput, Navid Aghdaie
  • Patent number: 12055947
    Abstract: Systems and techniques for updating floor plans for use by autonomous mobile devices. The techniques include accessing a first floor plan with associated spatial metadata. An updated occupancy map is received with additional geographic updates over the first floor plan. A transformation of the first floor plan is determined to match the new occupancy map. The spatial data and the first floor plan are transformed and the transformed spatial metadata is associated with the new occupancy map to form a second floor plan.
    Type: Grant
    Filed: December 8, 2021
    Date of Patent: August 6, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Nikhil Sharma, Tiago Etiene Queiroz, Prashant Anand Srivastava, Tushar Agarwal, Gaurav Guruprasad Manur, Aarthi Raveendran
  • Patent number: 11949800
    Abstract: Apparatus, systems and methods for providing a four-part, virtual reality (VR) customer service interaction between a customer service avatar operating on a VR platform and a customer using both a mobile device and a VR device are provided. Methods may include activating a VR session between the customer service avatar and the customer. Methods may include validating the VR session between the customer service avatar and the customer. Methods may include processing a co-browsing VR session request. Methods may include initiating the VR session between the customer service avatar and the customer.
    Type: Grant
    Filed: May 10, 2022
    Date of Patent: April 2, 2024
    Assignee: Bank of America Corporation
    Inventors: Tushar Agarwal, Sandeep Kumar Chauhan, Nandini Rathaur, Vasuki Anand, Amardeep Singh Talwar, Pushpa Neelakantan, Shailendra Singh
  • Publication number: 20230370290
    Abstract: Apparatus, systems and methods for providing a four-part, virtual reality (VR) customer service interaction between a customer service avatar operating on a VR platform and a customer using both a mobile device and a VR device are provided. Methods may include activating a VR session between the customer service avatar and the customer. Methods may include validating the VR session between the customer service avatar and the customer. Methods may include processing a co-browsing VR session request. Methods may include initiating the VR session between the customer service avatar and the customer.
    Type: Application
    Filed: May 10, 2022
    Publication date: November 16, 2023
    Inventors: Tushar Agarwal, Sandeep Kumar Chauhan, Nandini Rathaur, Vasuki Anand, Amardeep Singh Talwar, Pushpa Neelakantan, Shailendra Singh
  • Patent number: 11789914
    Abstract: Method and system for providing ground truth dataset and use thereof for improving data correctness. Datasets comprising data elements are received from different sources, each data element including an identifier and at least one attribute value associated therewith. Data correctness values are determined for the attribute values, each associated with a probability that an attribute value is correct. Data element with single data correctness value is added to the ground truth dataset for each attribute value for each identifier with which a respective attribute value is associated based on the determined data correctness values for the attribute values, whereby the data correctness values in the ground truth dataset define probability distributions of data correctness for the attribute values. Data correctness values for attribute values of data elements of a new dataset can be determined based on overlapping data compared in the ground truth dataset and the new dataset.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: October 17, 2023
    Assignee: zeotap GmbH
    Inventors: Swapnasarit Sahu, Ernest Kirubakaran Selvaraj, Tushar Agarwal, Projjol Banerjea, Daniel Heer, Sathish Kumar K S
  • Publication number: 20230039540
    Abstract: An example method of automated selection of audio asset synthesizing pipelines includes: receiving an audio stream comprising human speech; determining one or more features of the audio stream; selecting, based on the one or more features of the audio stream, an audio asset synthesizing pipeline; training, using the audio stream, one or more audio asset synthesizing models implementing respective stages of the selected audio asset synthesizing pipeline; and responsive to determining that a quality metric of the audio asset synthesizing pipeline satisfies a predetermined quality condition, synthesizing one or more audio assets by the selected audio asset synthesizing pipeline.
    Type: Application
    Filed: October 20, 2022
    Publication date: February 9, 2023
    Inventors: Kilol Gupta, Tushar Agarwal, Zahra Shakeri, Mohsen Sardari, Harold Henry Chaput, Navid Aghdaie
  • Patent number: 11526367
    Abstract: Systems and methods for translation of a digital document to an equivalent interactive User Interface (UI), receive the digital document containing content; detect a selection and placement of a plurality of form fields, based at least in part on the content; construct a UI template and corresponding object graph, based at least in part on the selection and placement of each of the plurality of form fields; wherein the UI template represents the content of the digital document according to a predefined document schema; and wherein the object graph is defined by one or more dependencies and one or more validations associated with the selection and placement of each of the plurality of form fields; parse the UI template; and render the UI template as an interactive UI for distribution to an end user based at least in part on a predefined rendering library.
    Type: Grant
    Filed: May 21, 2021
    Date of Patent: December 13, 2022
    Assignee: Morgan Stanley Services Group Inc.
    Inventors: Arun Nair, Anand Verma, Tushar Agarwal
  • Patent number: 11521594
    Abstract: An example method of automated selection of audio asset synthesizing pipelines includes: receiving an audio stream comprising human speech; determining one or more features of the audio stream; selecting, based on the one or more features of the audio stream, an audio asset synthesizing pipeline; training, using the audio stream, one or more audio asset synthesizing models implementing respective stages of the selected audio asset synthesizing pipeline; and responsive to determining that a quality metric of the audio asset synthesizing pipeline satisfies a predetermined quality condition, synthesizing one or more audio assets by the selected audio asset synthesizing pipeline.
    Type: Grant
    Filed: November 10, 2020
    Date of Patent: December 6, 2022
    Assignee: Electronic Arts Inc.
    Inventors: Kilol Gupta, Tushar Agarwal, Zahra Shakeri, Mohsen Sardari, Harold Henry Chaput, Navid Aghdaie
  • Publication number: 20220374249
    Abstract: Systems and methods for translation of a digital document to an equivalent interactive User Interface (UI), receive the digital document containing content; detect a selection and placement of a plurality of form fields, based at least in part on the content; construct a UI template and corresponding object graph, based at least in part on the selection and placement of each of the plurality of form fields; wherein the UI template represents the content of the digital document according to a predefined document schema; and wherein the object graph is defined by one or more dependencies and one or more validations associated with the selection and placement of each of the plurality of form fields; parse the UI template; and render the UI template as an interactive UI for distribution to an end user based at least in part on a predefined rendering library.
    Type: Application
    Filed: May 21, 2021
    Publication date: November 24, 2022
    Applicant: Morgan Stanley Services Group Inc.
    Inventors: Arun NAIR, Anand Verma, Tushar Agarwal
  • Publication number: 20220148561
    Abstract: An example method of automated selection of audio asset synthesizing pipelines includes: receiving an audio stream comprising human speech; determining one or more features of the audio stream; selecting, based on the one or more features of the audio stream, an audio asset synthesizing pipeline; training, using the audio stream, one or more audio asset synthesizing models implementing respective stages of the selected audio asset synthesizing pipeline; and responsive to determining that a quality metric of the audio asset synthesizing pipeline satisfies a predetermined quality condition, synthesizing one or more audio assets by the selected audio asset synthesizing pipeline.
    Type: Application
    Filed: November 10, 2020
    Publication date: May 12, 2022
    Inventors: Kilol Gupta, Tushar Agarwal, Zahra Shakeri, Mohsen Sardari, Harold Henry Chaput, Navid Aghdaie
  • Publication number: 20210365420
    Abstract: The present invention relates to providing a ground truth dataset and optimizing data correctness using the ground truth dataset. A plurality of datasets is received from different data sources. The datasets comprise a plurality of data elements. Each data element includes an identifier and at least one attribute value associated with the identifier. Data correctness values are determined for the attribute values. A data correctness value is associated with a probability that an attribute value is correct. A data element with a single data correctness value is added to the ground truth dataset for each attribute value for each identifier with which a respective attribute value is associated based on the determined data correctness values for the attribute values such that the data correctness values in the ground truth dataset define probability distributions of data correctness for the attribute values.
    Type: Application
    Filed: May 20, 2020
    Publication date: November 25, 2021
    Applicant: zeotap GmbH
    Inventors: Swapnasarit Sahu, Ernest Kirubakaran Selvaraj, Tushar Agarwal, Projjol Banerjea, Daniel Heer
  • Patent number: 10835823
    Abstract: Systems presented herein may automatically and dynamically modify a video game being played by a user based at least in part on a determined or predicted emotional state of a user. Using one or more machine learning algorithms, a parameter function can be generated that uses sensory and/or biometric data obtained by monitoring a user playing a video game. Based on the sensory and/or biometric data, an emotional state of the user can be predicted. For example, it can be determined whether a user is likely to be bored, happy, or frightened while playing the video game. Based at least in part on the determination of the user's emotional state, the video game can be modified to improve positive feelings and reduce negative feelings occurring in response to the video game.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: November 17, 2020
    Assignee: Electronic Arts Inc.
    Inventors: Chinmay Mukund Sumant, Nitish Victor, Tushar Agarwal, Preethi Ganeshan, Sundeep Narravula, Yu Jin, John Kolen, Navid Aghdaie, Kazi Atif-Uz Zaman
  • Patent number: 10841236
    Abstract: A system can manage distribution of computing jobs among a plurality of third-party network or cloud computing providers to maximize utilization of available computing resources purchased or otherwise obtained by an entity. The system can determine a dependency relationship between jobs and distribute the jobs among the network computing providers based at least in part on the dependency relationship between the jobs. Moreover, the system can use machine learning algorithms to generate one or more prediction algorithms to predict future computing resource usage demands for performing a set of scheduled and unscheduled jobs.
    Type: Grant
    Filed: March 30, 2018
    Date of Patent: November 17, 2020
    Assignee: Electronic Arts Inc.
    Inventors: Yu Jin, Sundeep Narravula, Navid Aghdaie, Kazi Atif-Uz Zaman, Preethi Ganeshan, Tushar Agarwal, Cong Feng, Drew John Zagieboylo
  • Publication number: 20200206631
    Abstract: Systems presented herein may automatically and dynamically modify a video game being played by a user based at least in part on a determined or predicted emotional state of a user. Using one or more machine learning algorithms, a parameter function can be generated that uses sensory and/or biometric data obtained by monitoring a user playing a video game. Based on the sensory and/or biometric data, an emotional state of the user can be predicted. For example, it can be determined whether a user is likely to be bored, happy, or frightened while playing the video game. Based at least in part on the determination of the user's emotional state, the video game can be modified to improve positive feelings and reduce negative feelings occurring in response to the video game.
    Type: Application
    Filed: December 27, 2018
    Publication date: July 2, 2020
    Inventors: Chinmay Mukund Sumant, Nitish Viktor, Tushar Agarwal, Preethi Ganeshan, Sundeep Narravula, Yu Jin, John Kolen, Navid Aghdaie, Kazi Atif-Uz Zaman
  • Publication number: 20060015335
    Abstract: A technique to link an audio enabled device with a speech driven application without specifying the specific ones of the audio enabled device-independent, speech driven application-independent, and speech application platform independent parameters. In one example embodiment, this is accomplished by using voice framework that receives and transmits digitized speech audio without specifying the specific ones of the audio enabled device-independent and speech application platform-independent parameters. The voice framework then converts the received digital speech audio to computer readable text. Further, the voice framework receives and transmits the computer readable text to the speech driven application without specifying the specific ones of the speech driven application-independent and speech application platform-independent parameters. The voice framework then converts the computer readable text to the digital speech audio.
    Type: Application
    Filed: July 13, 2004
    Publication date: January 19, 2006
    Inventors: Ravigopal Vennelakanti, Tushar Agarwal