Patents by Inventor Alexander B. Graves

Alexander B. Graves 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).

  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 11756535
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.
    Type: Grant
    Filed: March 21, 2022
    Date of Patent: September 12, 2023
    Assignee: Google LLC
    Inventor: Alexander B. Graves
  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 11282506
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.
    Type: Grant
    Filed: September 4, 2020
    Date of Patent: March 22, 2022
    Assignee: Google LLC
    Inventor: Alexander B. Graves
  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 10770064
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.
    Type: Grant
    Filed: October 21, 2019
    Date of Patent: September 8, 2020
    Assignee: Google LLC
    Inventor: Alexander B. Graves
  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 10453446
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.
    Type: Grant
    Filed: February 4, 2019
    Date of Patent: October 22, 2019
    Assignee: Google LLC
    Inventor: Alexander B. Graves
  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 10199038
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.
    Type: Grant
    Filed: February 12, 2016
    Date of Patent: February 5, 2019
    Assignee: Google LLC
    Inventor: Alexander B. Graves
  • System and method for speech recognition using deep recurrent neural networks
    Patent number: 9263036
    Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularization.
    Type: Grant
    Filed: November 26, 2013
    Date of Patent: February 16, 2016
    Assignee: Google Inc.
    Inventor: Alexander B. Graves