Patents by Inventor Andrey Eltsov
Andrey Eltsov 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: 11935537Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: GrantFiled: April 19, 2023Date of Patent: March 19, 2024Assignee: Roku, Inc.Inventors: Frank Maker, Andrey Eltsov, Robert Curtis, Gregory Medding
-
Publication number: 20230252992Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: ApplicationFiled: April 19, 2023Publication date: August 10, 2023Applicant: Roku, Inc.Inventors: Frank MAKER, Andrey ELTSOV, Robert CURTIS, Gregory MEDDING
-
Patent number: 11664026Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: GrantFiled: August 26, 2021Date of Patent: May 30, 2023Assignee: Roku, Inc.Inventors: Frank Maker, Andrey Eltsov, Robert Curtis, Gregory Medding
-
Patent number: 11611827Abstract: System, method, and various embodiments for providing a speaker audio configuration system are described herein. An embodiment operates by identifying an external speaker connected to an audio device. Second capability information for the external speaker is retrieved and user input indicating a relative position of the external speaker to the internal speaker is received. An audio configuration for the external speaker is calculated based on the second capability information and the relative position of the external speaker. The calculated audio configuration is provided to the external speaker. The external speaker is configured to receive and audibly output audio from the audio device based on the audio configuration.Type: GrantFiled: November 16, 2021Date of Patent: March 21, 2023Assignee: Roku, Inc.Inventors: Robert Curtis, Kasper Andersen, Andrey Eltsov, Mark Janossy
-
Publication number: 20220078553Abstract: System, method, and various embodiments for providing a speaker audio configuration system are described herein. An embodiment operates by identifying an external speaker connected to an audio device. Second capability information for the external speaker is retrieved and user input indicating a relative position of the external speaker to the internal speaker is received. An audio configuration for the external speaker is calculated based on the second capability information and the relative position of the external speaker. The calculated audio configuration is provided to the external speaker. The external speaker is configured to receive and audibly output audio from the audio device based on the audio configuration.Type: ApplicationFiled: November 16, 2021Publication date: March 10, 2022Inventors: ROBERT CURTIS, KASPER ANDERSEN, ANDREY ELTSOV, MARK JANOSSY
-
Patent number: 11212615Abstract: System, method, and various embodiments for providing a speaker normalization system are described herein. An embodiment operates by identifying a plurality of speakers connected to an audio device, wherein the audio device includes an internal speaker for which first capability information is known. Second capability information of each of the plurality of speakers is retrieved. User input indicating a relative position of each speaker is received. An audio configuration is calculated based on the second capability information and the relative position of each of the plurality of speakers. The calculated audio configuration is provided to each of the plurality of speakers, wherein each of the plurality of speakers is configured to receive and audibly output audio from the audio device based on the audio configuration.Type: GrantFiled: January 14, 2021Date of Patent: December 28, 2021Assignee: ROKU, INC.Inventors: Robert Curtis, Kasper Andersen, Andrey Eltsov, Mark Janossy
-
Publication number: 20210383807Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: ApplicationFiled: August 26, 2021Publication date: December 9, 2021Inventors: Frank MAKER, Andrey ELTSOV, Robert CURTIS, Gregory MEDDING
-
Patent number: 11145298Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: GrantFiled: February 13, 2018Date of Patent: October 12, 2021Assignee: Roku, Inc.Inventors: Frank Maker, Andrey Eltsov, Robert Curtis, Gregory Medding
-
Publication number: 20210176562Abstract: System, method, and various embodiments for providing a speaker normalization system are described herein. An embodiment operates by identifying a plurality of speakers connected to an audio device , wherein the audio device includes an internal speaker for which first capability information is known. Second capability information of each of the plurality of speakers is retrieved. User input indicating a relative position of each speaker is received. An audio configuration is calculated based on the second capability information and the relative position of each of the plurality of speakers. The calculated audio configuration is provided to each of the plurality of speakers, wherein each of the plurality of speakers is configured to receive and audibly output audio from the audio device based on the audio configuration.Type: ApplicationFiled: January 14, 2021Publication date: June 10, 2021Inventors: Robert Curtis, Kasper Andersen, Andrey Eltsov, Mark Janossy
-
Patent number: 10924853Abstract: System, method, and various embodiments for providing a speaker normalization system are described herein. An embodiment operates by identifying a plurality of audio output devices connected to an audio source. For each audio output device, a set of technical capabilities and a relative position of the audio output device is identified. An audio configuration is calculated based on both the set of technical capabilities and the relative position of each audio output device, and which audio output devices are identified. The calculated audio configuration is provided to each identified audio output device. Audio is provided to each of the identified audio output devices.Type: GrantFiled: December 4, 2019Date of Patent: February 16, 2021Assignee: ROKU, INC.Inventors: Robert Curtis, Kasper Andersen, Andrey Eltsov, Mark Janossy
-
Publication number: 20190251960Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.Type: ApplicationFiled: February 13, 2018Publication date: August 15, 2019Inventors: Frank MAKER, Andrey Eltsov, Robert Curtis, Gregory Medding