Patents by Inventor NATHAN BLAYLOCK

NATHAN BLAYLOCK 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: 20240395281
    Abstract: A health condition or change in health condition of a person may be determined by processing the person's speech with a neural network. Speech from more than one time period may be processed and, in some implementations, speech from a time period may be associated with a health condition label. For each time period, a feature vector may be computed from the speech and the feature vector may be processed with a neural network to obtain a speech embedding vector. In some implementations, feature vector may include word-piece encodings and the neural network may be a transformer neural network. The speech embedding vectors may be processed with a mathematical model to determine a change in a health condition between two time periods or to determine a health condition label for a specific time period. In some implementations, the mathematical model may be a regression model or a fully-connected neural network.
    Type: Application
    Filed: August 6, 2024
    Publication date: November 28, 2024
    Applicant: Canary Speech, Inc.
    Inventors: SAMUEL KIM, NAMHEE KWON, NATHAN BLAYLOCK, HENRY J. O'CONNELL, JEFFREY P. ADAMS
  • Patent number: 12125497
    Abstract: A health condition or change in health condition of a person may be determined by processing the person's speech with a neural network. Speech from more than one time period may be processed and, in some implementations, speech from a time period may be associated with a health condition label. For each time period, a feature vector may be computed from the speech and the feature vector may be processed with a neural network to obtain a speech embedding vector. In some implementations, feature vector may include word-piece encodings and the neural network may be a transformer neural network. The speech embedding vectors may be processed with a mathematical model to determine a change in a health condition between two time periods or to determine a health condition label for a specific time period. In some implementations, the mathematical model may be a regression model or a fully-connected neural network.
    Type: Grant
    Filed: September 7, 2021
    Date of Patent: October 22, 2024
    Assignee: CANARY SPEECH, LLC
    Inventors: Samuel Kim, Namhee Kwon, Nathan Blaylock, Henry J. O'Connell, Jeffrey P. Adams
  • Publication number: 20240174385
    Abstract: ThermaSatâ„¢ propulsion system uses water as a safe and non-explosive propellant, and which is unpressurized at liftoff. Utilizing solar thermal propulsion, the compact and efficient capacitor heats water to steam to produce high thrust and total impulse. The advanced optical system allows for the thermal capacitor to charge through solar power alone with no protruding concentrators or power draw from the main bus. Additional solar panels, body mounted to the ThermaSat, provide auxiliary heating of the thermal capacitor when not directly incident to sunlight to promote non-sun pointing operations. Additionally, a conductive insulative system or method can include a phase change material and an insulated thermal capacitor wrapped in an insulative material including an inner layer of a high temperature multi-layer insulation and an outer layer of low temperature multi-layer insulation and the outside of the outer layer is covered with a reflective material.
    Type: Application
    Filed: November 2, 2023
    Publication date: May 30, 2024
    Applicant: THERMASAT, INC.
    Inventors: TROY MICHAEL HOWE, JACK R. MILLER, CHRIS CASTELLI, NATHAN BLAYLOCK
  • Publication number: 20230072242
    Abstract: A health condition or change in health condition of a person may be determined by processing the person's speech with a neural network. Speech from more than one time period may be processed and, in some implementations, speech from a time period may be associated with a health condition label. For each time period, a feature vector may be computed from the speech and the feature vector may be processed with a neural network to obtain a speech embedding vector. In some implementations, feature vector may include word-piece encodings and the neural network may be a transformer neural network. The speech embedding vectors may be processed with a mathematical model to determine a change in a health condition between two time periods or to determine a health condition label for a specific time period. In some implementations, the mathematical model may be a regression model or a fully-connected neural network.
    Type: Application
    Filed: September 7, 2021
    Publication date: March 9, 2023
    Applicant: Canary Speech, LLC
    Inventors: SAMUEL KIM, NAMHEE KWON, NATHAN BLAYLOCK, HENRY J. O'CONNELL, JEFFREY P. ADAMS