Patents by Inventor Matthew James Beal

Matthew James Beal 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).

  • Speaker detection and tracking using audiovisual data
    Patent number: 8842177
    Abstract: Object tracking includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.
    Type: Grant
    Filed: March 31, 2010
    Date of Patent: September 23, 2014
    Assignee: Microsoft Corporation
    Inventors: Matthew James Beal, Nebojsa Jojic, Hagai Attias
  • SPEAKER DETECTION AND TRACKING USING AUDIOVISUAL DATA
    Publication number: 20100194881
    Abstract: Object tracking includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.
    Type: Application
    Filed: March 31, 2010
    Publication date: August 5, 2010
    Applicant: Microsoft Corporation
    Inventors: Matthew James Beal, Nebojsa Jojic, Hagai Attias
  • Speaker detection and tracking using audiovisual data
    Patent number: 7692685
    Abstract: A system and method facilitating object tracking is provided. The invention includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.
    Type: Grant
    Filed: March 31, 2005
    Date of Patent: April 6, 2010
    Assignee: Microsoft Corporation
    Inventors: Matthew James Beal, Nebojsa Jojic, Hagai Attias
  • Speaker detection and tracking using audiovisual data
    Patent number: 6940540
    Abstract: A system and method facilitating object tracking is provided. The system includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.
    Type: Grant
    Filed: June 27, 2002
    Date of Patent: September 6, 2005
    Assignee: Microsoft Corporation
    Inventors: Matthew James Beal, Nebojsa Jojic, Hagai Attias
  • Speaker detection and tracking using audiovisual data
    Publication number: 20040001143
    Abstract: A system and method facilitating object tracking is provided. The invention includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.
    Type: Application
    Filed: June 27, 2002
    Publication date: January 1, 2004
    Inventors: Matthew James Beal, Nebojsa Jojic, Hagai Attias