Patents by Inventor Kenneth John Basye

Kenneth John Basye 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: 11978478
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Grant
    Filed: March 13, 2023
    Date of Patent: May 7, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Publication number: 20230395095
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Application
    Filed: March 13, 2023
    Publication date: December 7, 2023
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Patent number: 11657804
    Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
    Type: Grant
    Filed: November 5, 2020
    Date of Patent: May 23, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Rohit Prasad, Kenneth John Basye, Spyridon Matsoukas, Rajiv Ramachandran, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister
  • Patent number: 11651780
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Grant
    Filed: June 7, 2021
    Date of Patent: May 16, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Patent number: 11322152
    Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.
    Type: Grant
    Filed: June 17, 2019
    Date of Patent: May 3, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Hugh Evan Secker-Walker, Tony David, Reinhard Kneser, Jeffrey Penrod Adams, Stan Weidner Salvador, Mahesh Krishnamoorthy
  • Publication number: 20220059124
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Application
    Filed: June 7, 2021
    Publication date: February 24, 2022
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Patent number: 11037584
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: June 15, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Publication number: 20210134276
    Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
    Type: Application
    Filed: November 5, 2020
    Publication date: May 6, 2021
    Inventors: Rohit Prasad, Kenneth John Basye, Spyridon Matsoukas, Rajiv Ramachandran, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister
  • Patent number: 10832662
    Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
    Type: Grant
    Filed: July 3, 2017
    Date of Patent: November 10, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Rohit Prasad, Kenneth John Basye, Spyridon Matsoukas, Rajiv Ramachandran, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister
  • Publication number: 20200194032
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Application
    Filed: December 16, 2019
    Publication date: June 18, 2020
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Patent number: 10566012
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Grant
    Filed: October 12, 2018
    Date of Patent: February 18, 2020
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Publication number: 20200043499
    Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.
    Type: Application
    Filed: June 17, 2019
    Publication date: February 6, 2020
    Inventors: Kenneth John Basye, Hugh Evan Secker-Walker, Tony David, Reinhard Kneser, Jeffrey Penrod Adams, Stan Weidner Salvador, Mahesh Krishnamoorthy
  • Patent number: 10325598
    Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.
    Type: Grant
    Filed: July 10, 2017
    Date of Patent: June 18, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Hugh Evan Secker-Walker, Tony David, Reinhard Kneser, Jeffrey Penrod Adams, Stan Weidner Salvador, Mahesh Krishnamoorthy
  • Patent number: 10102850
    Abstract: A speech recognition system utilizing automatic speech recognition techniques such as end-pointing techniques in conjunction with beamforming and/or signal processing to isolate speech from one or more speaking users from multiple received audio signals and to detect the beginning and/or end of the speech based at least in part on the isolation. Audio capture devices such as microphones may be arranged in a beamforming array to receive the multiple audio signals. Multiple audio sources including speech may be identified in different beams and processed.
    Type: Grant
    Filed: February 25, 2013
    Date of Patent: October 16, 2018
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Kenneth John Basye, Jeffrey Penrod Adams
  • Publication number: 20180096689
    Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.
    Type: Application
    Filed: July 10, 2017
    Publication date: April 5, 2018
    Inventors: Kenneth John Basye, Hugh Evan Secker-Walker, Tony David, Reinhard Kneser, Jeffrey Penrod Adams, Stan Weidner Salvador, Mahesh Krishnamoorthy
  • Publication number: 20180012593
    Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
    Type: Application
    Filed: July 3, 2017
    Publication date: January 11, 2018
    Inventors: Rohit Prasad, Kenneth John Basye, Spyridon Matsoukas, Rajiv Ramachandran, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister
  • Patent number: 9818407
    Abstract: An efficient audio streaming method and apparatus includes a client process implemented on a client or local device and a server process implemented on a remote server or server(s). The client process and server process each have speech recognition components and communicate over a network, and together efficiently manage the detection of speech in an audio signal streamed by the local device to the server for speech recognition and potentially further processing at the server. The client process monitors audio input and in a first detection stage, implements endpointing on the local device to determine when speech is detected. The client process may further determine if a “wakeword” is detected, and then the client process opens a connection and begins streaming audio to the server process via the network.
    Type: Grant
    Filed: February 7, 2013
    Date of Patent: November 14, 2017
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Hugh Evan Secker-Walker, Kenneth John Basye, Nikko Strom, Ryan Paul Thomas
  • Patent number: 9704486
    Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.
    Type: Grant
    Filed: December 11, 2012
    Date of Patent: July 11, 2017
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth John Basye, Hugh Evan Secker-Walker, Tony David, Reinhard Kneser, Jeffrey Penrod Adams, Stan Weidner Salvador, Mahesh Krishnamoorthy
  • Patent number: 9697828
    Abstract: Features are disclosed for detecting words in audio using environmental information and/or contextual information in addition to acoustic features associated with the words to be detected. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
    Type: Grant
    Filed: June 20, 2014
    Date of Patent: July 4, 2017
    Assignee: Amazon Technologies, Inc.
    Inventors: Rohit Prasad, Kenneth John Basye, Spyridon Matsoukas, Rajiv Ramachandran, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister
  • Patent number: 9613624
    Abstract: In a dynamic automatic speech recognition (ASR) processing system, ASR processing may be configured to estimate a latency of returning speech results to a user based on work being done by an ASR processor. The ASR processing system may measure work done by an ASR processor by measuring one or more time independent metrics and comparing the metrics to threshold values. If the metrics exceed the thresholds, the ASR system may take steps to reduce latency associated with processing the utterance, including adjusting a speech recognition parameter.
    Type: Grant
    Filed: June 25, 2014
    Date of Patent: April 4, 2017
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Jake Simon Kramer, Alexander David Rosen, Kenneth John Basye