Speech recognition for avionic systems

• US 9,824,689 B1
• Filed: 12/07/2015
• Issued: 11/21/2017
• Est. Priority Date: 12/07/2015
• Status: Active Grant

• Current Assignee: Rockwell Collins, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: Rockwell Collins, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Shapiro, Geoffrey A.
• Primary Examiner(s): Guerra-Erazo, Edgar
• Application Number:
  US14/961,536
• Time in Patent Office: 715 Days
• Field of Search: 704270, 7042701, 704275, 704277
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

Voice-operable avionic systems and methods supporting utilization of speech recognition to facilitate control of avionic systems are disclosed. Utilizing speech recognition to control avionic systems may help reduce the head-down time of the flight crew. Safety features may also be implemented to ensure safety-critical commands are carried out as intended when commands are received through speech recognition. In addition, voice-operable avionic systems configured in accordance with embodiments of the inventive concepts disclosed herein may be implemented in manners that can help reduce the complexity and cost associated with obtaining certifications from aviation authorities.

Claims

1. A system, comprising:

an audio device configured to receive an audio input from a user;

a speech recognition processor in communication with the audio device, the speech recognition processor configured to recognize at least one voice command from the audio input; and

an electronic device separated from the speech recognition processor and in communication with the speech recognition processor, the electronic device configured to;

determine whether the at least one voice command is valid and includes a safety-critical command;

present a preview of the at least one voice command when the at least one voice command includes a safety-critical command; and

execute the at least one voice command only after receiving an explicit confirmation from the user when the at least one voice command includes a safety-critical command.

2. The system of claim 1, wherein the at least one voice command is determined to be valid based on a set of rules and the at least one voice command is determined to be invalid based on the at least one voice command containing a first value or a request that is above or beyond a second value or limit set by the set of rules.

3. The system of claim 1, wherein the preview of the at least one voice command includes an audible feedback to the user.

4. The system of claim 1, wherein at least one of the speech recognition processor and the electronic device is further configured to:

cancel the at least one voice command when at least one of the following occurs;

no explicit confirmation is received from the user within a configurable time period;

a cancellation command is received; and

a new audio input is received from the user.

5. The system of claim 1, wherein at least one of the speech recognition processor and the electronic device is further configured to:

determine whether the at least one voice command includes a safety-critical command; and

execute the at least one voice command immediately when the at least one voice command does not include a safety-critical command.

6. The system of claim 5, wherein at least one of the speech recognition processor and the electronic device is further configured to:

provide the user an option to reverse the execution of the at least one voice command.

7. The system of claim 1, wherein at least one of the speech recognition processor and the electronic device is further configured to:

reject the at least one voice command when the at least one voice command is determined to be invalid.

8. The system of claim 7, wherein the rejection of the at least one voice command is audible to the user.

9. The system of claim 1, wherein the electronic device is an avionic system located onboard an aircraft.

10. The system of claim 9, wherein the speech recognition processor and the avionic system maintain a separation that allows the speech recognition processor and the avionic system to be certified independently with respect to each other.

11. The system of claim 9, wherein the audio device is further configured to receive audio inputs by monitoring radio communications.

12. A method, comprising:

receiving an audio input from a user;

processing the audio input to recognize at least one voice command from the audio input;

determining whether the at least one voice command is valid;

processing the at least one voice command when the at least one voice command is determined to be valid, further comprising;

determining whether the at least one voice command includes a safety-critical command;

presenting a preview of the at least one voice command when the at least one voice command includes a safety-critical command; and

executing the at least one voice command only after receiving an explicit confirmation from the user when the at least one voice command includes a safety-critical command.

13. The method of claim 12, wherein the processing of the at least one voice command further comprises:

canceling the at least one voice command if no explicit confirmation is received from the user within a configurable time period.

14. The method of claim 12, wherein the processing of the at least one voice command further comprises:

executing the at least one voice command immediately when the at least one voice command does not include a safety-critical command.

15. The method of claim 14, wherein the processing of the at least one voice command further comprises:

providing the user an option to reverse the execution of the at least one voice command.

16. The method of claim 12, further comprising:

rejecting the at least one voice command when the at least one voice command is determined to be invalid.

17. The method of claim 12, further comprising:

providing an audible feedback to the user regarding processing status of the at least one voice command.

18. The method of claim 12, further comprising:

collecting data regarding at least one of the audio input and the at least one voice command; and

analyzing the data collected to improve accuracy of recognition of the at least one voice command from the audio input.

19. A system, comprising:

an audio device configured to receive an audio input from a user;

a speech recognition processor in communication with the audio device, the speech recognition processor configured to recognize at least one voice command from the audio input; and

an avionic system separated from the speech recognition processor and in communication with the speech recognition processor, the avionic system configured to;

determine whether the at least one voice command is valid;

determine whether the at least one voice command includes a safety-critical command;

present a preview of the at least one voice command when the at least one voice command is valid and includes a safety-critical command;

execute the at least one voice command only after receiving an explicit confirmation from the user when the at least one voice command is valid and includes a safety-critical command; and

execute the at least one voice command immediately when the at least one voice command is valid and does not include a safety-critical command.

20. The system of claim 19, wherein the at least one voice command includes at least one of:

a flight display control command, a flight management system control command, a chart recall command, a radio tuning command, a format change command, a checklist entry command, an aircraft system command, a switch control command, a menu control command, a natural language command, a macro command, and a contextual command.