Patents by Inventor Abesh Thakur

Abesh Thakur 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).

  • Patent number: 10382881
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Grant
    Filed: October 11, 2018
    Date of Patent: August 13, 2019
    Assignee: Facebook, Inc.
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair
  • Publication number: 20190158973
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Application
    Filed: October 11, 2018
    Publication date: May 23, 2019
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair
  • Patent number: 10123149
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Grant
    Filed: May 11, 2018
    Date of Patent: November 6, 2018
    Assignee: Facebook, Inc.
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair
  • Publication number: 20180262860
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Application
    Filed: May 11, 2018
    Publication date: September 13, 2018
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair
  • Patent number: 10028072
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Grant
    Filed: August 9, 2016
    Date of Patent: July 17, 2018
    Assignee: Facebook, Inc.
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair
  • Publication number: 20170208417
    Abstract: Embodiments relate to, for a scene comprising a representation of at least one object and at least one sound source: obtaining a decomposition of the at least one object, the decomposition comprising at least one geometric component; modelling at least one interaction of the at least one object and the at least one sound source using the at least one geometric component; and, in dependence on the modelling of the at least one interaction, processing an audio input associated with the at least one sound source to obtain an audio output.
    Type: Application
    Filed: August 9, 2016
    Publication date: July 20, 2017
    Inventors: Abesh Thakur, Ross Taylor, Tobias Graham Fone Carpenter, Varun Nair