ADAPTIVE SPEECH RECOGNITION METHODS AND SYSTEMS

    公开(公告)号:US20220343897A1

    公开(公告)日:2022-10-27

    申请号:US17659596

    申请日:2022-04-18

    Abstract: Methods and systems are provided for assisting operation of a vehicle using speech recognition. One method involves analyzing a transcription of an audio communication with respect to the vehicle to characterize a nonstandard pattern within the transcription of the audio communication, obtaining a ground truth for the transcription of the audio communication, determining one or more performance metrics associated with the nonstandard pattern within the transcription based on a relationship between the transcription of the audio communication and the ground truth for the transcription, updating a speech recognition vocabulary for the vehicle to include the nonstandard pattern based at least in part on the one or more performance metrics and determining an updated speech recognition model for the vehicle using the updated speech recognition vocabulary and the audio communication.

    System and method for providing contextual feedback in response to a command

    公开(公告)号:US12165639B2

    公开(公告)日:2024-12-10

    申请号:US17398609

    申请日:2021-08-10

    Abstract: A voice recognition system in an aircraft is provided. The voice recognition system includes: a voice recognition controller configured to receive a voice command from a flight crew member voice interface, convert the voice command to an avionics system command, and forward the avionics system command to an avionics system for execution. The voice recognition system further includes an application controller configured to: receive the avionics system command that has been converted from the voice command; determine whether the avionics system command can be performed; cause the avionics system command to be performed when it is determined that the avionics system command can be performed; and when it is determined that the avionics system command cannot be performed, generate a message that provides a reason why the avionics system command cannot be performed and cause the message to be displayed on a display device and/or annunciated on an aural device.

    SYSTEM AND METHOD FOR PROVIDING CONTEXTUAL FEEDBACK IN RESPONSE TO A COMMAND

    公开(公告)号:US20220084517A1

    公开(公告)日:2022-03-17

    申请号:US17398609

    申请日:2021-08-10

    Abstract: A voice recognition system in an aircraft is provided. The voice recognition system includes: a voice recognition controller configured to receive a voice command from a flight crew member voice interface, convert the voice command to an avionics system command, and forward the avionics system command to an avionics system for execution. The voice recognition system further includes an application controller configured to: receive the avionics system command that has been converted from the voice command; determine whether the avionics system command can be performed; cause the avionics system command to be performed when it is determined that the avionics system command can be performed; and when it is determined that the avionics system command cannot be performed, generate a message that provides a reason why the avionics system command cannot be performed and cause the message to be displayed on a display device and/or annunciated on an aural device.

    System and method for assisting pilot through clearance playback

    公开(公告)号:US11289094B2

    公开(公告)日:2022-03-29

    申请号:US16879383

    申请日:2020-05-20

    Abstract: Systems and methods are provided for playback clearance assistance, the system includes a processing system configured to: in response to receipt of a voice clearance communication comprising a clearance message, decode the clearance message to identify features contained within the clearance message related to a command instruction or clearance data for a flight; determine, at least one applicable clearance message amendment solution for use to amend the clearance message from a set of applicable clearance message amendment solutions wherein the applicable clearance amendment solution is determined based on keywords retrieved from a plurality of databases comprising at least contextual and prior clearance message data; and apply the applicable clearance message amendment solution to append keywords to the clearance message to generate an appended clearance message that reduces ambiguity in the clearance message resulting from at least missing value data, non-standard terminology or incomplete message information.

    Intent managing system
    8.
    发明授权

    公开(公告)号:US10095473B2

    公开(公告)日:2018-10-09

    申请号:US14931352

    申请日:2015-11-03

    Abstract: An intent managing system and a method for operating the same are provided. The system, for example, may include, but is not limited to a processor communicatively coupled to an input system and a memory. The processor may be configured to receive a voice command, determine how many of a plurality of voice controllable systems utilize the voice command, automatically select one of the plurality of voice controllable systems, generate an indication of the selected one of the plurality of voice controllable systems, receive, from the at least one input system, confirmation of the selected one of the plurality of voice controllable systems, and execute the received voice command at the selected one of the plurality of voice controllable systems when the confirmation is received.

    Adaptive speech recognition methods and systems

    公开(公告)号:US12190861B2

    公开(公告)日:2025-01-07

    申请号:US17659596

    申请日:2022-04-18

    Abstract: Methods and systems are provided for assisting operation of a vehicle using speech recognition. One method involves analyzing a transcription of an audio communication with respect to the vehicle to characterize a nonstandard pattern within the transcription of the audio communication, obtaining a ground truth for the transcription of the audio communication, determining one or more performance metrics associated with the nonstandard pattern within the transcription based on a relationship between the transcription of the audio communication and the ground truth for the transcription, updating a speech recognition vocabulary for the vehicle to include the nonstandard pattern based at least in part on the one or more performance metrics and determining an updated speech recognition model for the vehicle using the updated speech recognition vocabulary and the audio communication.

Patent Agency Ranking