Patents by Inventor Raphael Petegrosso

Raphael Petegrosso 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).

  • FEDERATED LEARNING FOR AUDIO PROCESSING
    Publication number: 20260031081
    Abstract: A system performs federated learning and retraining of a machine learning model used for processing audio detected by a user device. The system uses both gradient data (which may correspond to false-rejects) and audio data (which may correspond to false-positives) received from devices. The system may also use a teacher model to produce labels for data in an automated fashion, thus allowing retraining to happen in an unsupervised manner.
    Type: Application
    Filed: October 1, 2025
    Publication date: January 29, 2026
    Inventors: Andrew Morris Werchniak, Ilya Sokolov, Raphael Petegrosso, Aansh Shah, Aaron Challenner, Michael Thomas Peterson, Shuang Wu
  • Federated learning for audio processing
    Patent number: 12451122
    Abstract: A system performs federated learning and retraining of a machine learning model used for processing audio detected by a user device. The system uses both gradient data (which may correspond to false-rejects) and audio data (which may correspond to false-positives) received from devices. The system may also use a teacher model to produce labels for data in an automated fashion, thus allowing retraining to happen in an unsupervised manner.
    Type: Grant
    Filed: June 5, 2023
    Date of Patent: October 21, 2025
    Assignee: Amazon Technologies, Inc.
    Inventors: Andrew Morris Werchniak, Ilya Sokolov, Raphael Petegrosso, Aansh Shah, Aaron Challenner, Michael Thomas Peterson, Shuang Wu