Patents by Inventor Ajith Prabhakara
Ajith Prabhakara 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).
-
Publication number: 20230368780Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. If the DSP’s wakeword detection component detects a wakeword in speech, the companion application’s wakeword detection component may be used to determine whether the wakeword was spoken by the user of the device. If the companion application’s wakeword detection component determines the user spoke the wakeword, audio data representing the speech may be sent to at least one server(s) for processing.Type: ApplicationFiled: May 25, 2023Publication date: November 16, 2023Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 11694679Abstract: Techniques for processing incoming audio using multiple wakeword detectors are described. Audio data representing an utterance may be processed by different wakeword detectors that can detect different wakewords and are associated with different speech processing components. When a wakeword is detected by one of the wakeword detectors, it may be processed by the corresponding speech processing component.Type: GrantFiled: October 4, 2021Date of Patent: July 4, 2023Assignee: Amazon Technologies, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 11514900Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may initially include an untrained wakeword detection component. The wakeword detection component of the DSP may be trained by engaging a user to speak particular utterances. Once a companion application is configured to implement a wakeword detection component, the companion application's wakeword detection component may be trained specific to the user of the device. Once the companion application's wakeword detection component is trained, the DSP wakeword detection component may be deactivated or its accuracy adjusted.Type: GrantFiled: January 30, 2020Date of Patent: November 29, 2022Assignee: Amazon Technology, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 11373644Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. In response to determining that the user spoke the wakeword, the companion application may send audio data representing the speech and data corresponding to the user to at least one server(s) for processing. Further, the device may receive captured speech and captured image data corresponding to the captured speech and determine a representation of a user in the captured image data. If the device determines the user is represented in the image data, audio data representing the speech may be sent to at least one server(s) for processing.Type: GrantFiled: July 21, 2020Date of Patent: June 28, 2022Assignee: Amazon Technologies, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Publication number: 20220059084Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. If the DSP's wakeword detection component detects a wakeword in speech, the companion application's wakeword detection component may be used to determine whether the wakeword was spoken by the user of the device. If the companion application's wakeword detection component determines the user spoke the wakeword, audio data representing the speech may be sent to at least one server(s) for processing.Type: ApplicationFiled: October 4, 2021Publication date: February 24, 2022Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 11151988Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. If the DSP's wakeword detection component detects a wakeword in speech, the companion application's wakeword detection component may be used to determine whether the wakeword was spoken by the user of the device. If the companion application's wakeword detection component determines the user spoke the wakeword, audio data representing the speech may be sent to at least one server(s) for processing.Type: GrantFiled: January 31, 2020Date of Patent: October 19, 2021Assignee: Amazon Technolgies, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Publication number: 20200372901Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. If the DSP's wakeword detection component detects a wakeword in speech, the companion application's wakeword detection component may be used to determine whether the wakeword was spoken by the user of the device. If the companion application's wakeword detection component determines the user spoke the wakeword, audio data representing the speech may be sent to at least one server(s) for processing.Type: ApplicationFiled: July 21, 2020Publication date: November 26, 2020Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 10825451Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may initially include an untrained wakeword detection component. The wakeword detection component of the DSP may be trained by engaging a user to speak particular utterances. Once a companion application is configured to implement a wakeword detection component, the companion application's wakeword detection component may be trained specific to the user of the device. Once the companion application's wakeword detection component is trained, the DSP wakeword detection component may be deactivated or its accuracy adjusted.Type: GrantFiled: June 25, 2018Date of Patent: November 3, 2020Assignee: Amazon Technologies, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray
-
Patent number: 10762896Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may implement a wakeword detection component to detect when captured speech includes a wakeword. A companion application installed on the device may implement a wakeword detection component trained using speech of a user of the device. If the DSP's wakeword detection component detects a wakeword in speech, the companion application's wakeword detection component may be used to determine whether the wakeword was spoken by the user of the device. If the companion application's wakeword detection component determines the user spoke the wakeword, audio data representing the speech may be sent to at least one server(s) for processing.Type: GrantFiled: June 25, 2018Date of Patent: September 1, 2020Assignee: Amazon Technologies, Inc.Inventors: Deepak Yavagal, Ajith Prabhakara, John Gray