Patents by Inventor Krzysztof Czarnowski

Krzysztof Czarnowski 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).

  • On-device neural network adaptation with binary mask learning for language understanding systems
    Patent number: 11257483
    Abstract: Spoken language understanding techniques include training a dynamic neural network mask relative to a static neural network using only post-deployment training data such that the mask zeroes out some of the weights of the static neural network and allows some other weights to pass through and applying a dynamic neural network corresponding to the masked static neural network to input queries to identify outputs for the queries.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: February 22, 2022
    Assignee: Intel Corporation
    Inventors: Krzysztof Czarnowski, Munir Georges
  • ADAPTIVELY RECOGNIZING SPEECH USING KEY PHRASES
    Publication number: 20200090657
    Abstract: An example apparatus for recognizing speech includes an audio receiver to receive a stream of audio. The apparatus also includes a key phrase detector to detect a key phrase in the stream of audio. The apparatus further includes a model adapter to dynamically adapt a model based on the detected key phrase. The apparatus also includes a query recognizer to detect a voice query following the key phrase in a stream of audio via the adapted model.
    Type: Application
    Filed: November 22, 2019
    Publication date: March 19, 2020
    Applicant: INTEL CORPORATION
    Inventors: Krzysztof Czarnowski, Munir Nikolai Alexander Georges, Tobias Bocklet, Georg Stemmer
  • ON-DEVICE NEURAL NETWORK ADAPTATION WITH BINARY MASK LEARNING FOR LANGUAGE UNDERSTANDING SYSTEMS
    Publication number: 20190228763
    Abstract: Spoken language understanding techniques include training a dynamic neural network mask relative to a static neural network using only post-deployment training data such that the mask zeroes out some of the weights of the static neural network and allows some other weights to pass through and applying a dynamic neural network corresponding to the masked static neural network to input queries to identify outputs for the queries.
    Type: Application
    Filed: March 29, 2019
    Publication date: July 25, 2019
    Inventors: Krzysztof Czarnowski, Munir Georges