Patents by Inventor Piotr Rozen

Piotr Rozen 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).

  • IMPROVED FIXED POINT INTEGER IMPLEMENTATIONS FOR NEURAL NETWORKS
    Publication number: 20170220929
    Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include processing a node of the neural network by determining a score for the node as a product of weights and inputs such that the weights are fixed point integer values, applying a correction to the score based a correction value associated with at least one of the weights, and generating an output from the node based on the corrected score.
    Type: Application
    Filed: September 9, 2014
    Publication date: August 3, 2017
    Applicant: Intel Corporation
    Inventors: Piotr Rozen, Georg Stemmer
  • Frame skipping with extrapolation and outputs on demand neural network for automatic speech recognition
    Patent number: 9520128
    Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.
    Type: Grant
    Filed: September 23, 2014
    Date of Patent: December 13, 2016
    Assignee: Intel Corporation
    Inventors: Josef Bauer, Piotr Rozen, Georg Stemmer
  • Frame Skipping With Extrapolation and Outputs On Demand Neural Network For Automatic Speech Recognition
    Publication number: 20160086600
    Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.
    Type: Application
    Filed: September 23, 2014
    Publication date: March 24, 2016
    Inventors: Josef Bauer, Piotr Rozen, Georg Stemmer