VOICE ROUTER

• US 20160297543A1
• Filed: 04/07/2015
• Published: 10/13/2016
• Est. Priority Date: 04/07/2015
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Chen, Lucas, Li, Chao
• Granted Patent: US 9,546,005 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: B64D 47/00 Equipment not otherwise provided for
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A voice router for a vehicle and a method for operating a voice router are provided. The voice router, for example, may include, but is not limited to, an interface configured to be coupled to a microphone and a plurality of subsystems of an aircraft, and a processor coupled to the interface, the processor configured to receive, from the microphone, voice command audio data, convert, using an avionic language model, the voice command audio data into voice command text data, determine, using a distribution model, whether a command corresponding to the voice command text data can be executed, transmitting, to at least one of the plurality of subsystems, instructions to execute the command when the voice router determines that the command can be executed, and providing, using the output system, feedback when the command is executed.

Claims

1. An aircraft, comprising:

a plurality of subsystems;

an interface device; and

a voice router communicatively coupled to the interface device and to at least one of the plurality of subsystems, the voice router configured to;

receive, from the interface device, voice command audio data;

convert, using an avionic language model, the voice command audio data into voice command text data;

determine, using a distribution model, whether a command corresponding to the voice command text data can be executed; and

transmit, to at least one of the plurality of subsystems, instructions to execute the command when the voice router determines that the command can be executed.

2. The aircraft of claim 1, wherein the voice router is further configured to determine whether a command corresponding to the voice command text data can be executed by:

evaluating a rule corresponding to the command, wherein the rule is defined in the distribution model.

3. The aircraft of claim 2, wherein the voice router is further configured to determine whether a command corresponding to the voice command text data can be executed by:

requesting data for evaluating the rule from at least one of the plurality of subsystems.

4. The aircraft of claim 3, wherein the voice router determines from which of the at least one of the plurality of subsystems to request the data for evaluating the rule based upon the distribution model.

5. The aircraft of claim 1, wherein the distribution model includes rules for whether the command corresponding to the voice command text data can be executed and procedures for executing the command.

6. The aircraft of claim 1, wherein when the voice router determines that the command cannot be executed, the voice router outputs audio feedback.

7. The aircraft of claim 1, wherein the avionic language model defines vocabulary, grammar and command parameters for a plurality of voice commands.

8. The aircraft of claim 7, wherein the converting the voice command audio data into voice command text data further comprises:

performing speech recognition upon the voice command audio data; and

determining the voice command text data based upon an output of the speech recognition and the vocabulary, grammar and command parameters for the plurality of voice commands.

9. A method for controlling an aircraft, comprising:

receiving, by a voice router, audio data;

determining, by the voice router, a command corresponding to the audio data based upon an avionic language model;

determining, by the voice router, when the command can be executed based upon a distribution model; and

executing, when the voice router determines that the command can be executed, the command.

10. The method of claim 9, wherein the determining the command further comprises:

performing, by the voice router, speech recognition on the audio data to convert the audio data into text data; and

correlating, by the voice router, the text data to the command based upon grammar, vocabulary and command parameters of the text data to determine the command.

11. The method of claim 9, wherein the determining when the command can be executed further comprises:

evaluating, by the voice router, at least one rule corresponding to the command defined in the distribution model.

12. The method of claim 11, wherein the evaluating further comprises:

transmitting, by the voice route, a request for data for evaluating the at least one rule to at least one subsystem of the aircraft;

receiving, by the voice router, the requested data; and

evaluating, by the voice router, the at least one rule using the requested data.

13. The method of claim 11, wherein the transmitting further comprises:

determining, by the voice router, a format for instructing the at least one subsystem using the distribution model; and

transmitting, by the voice router, the request for data to the at least one subsystem of the aircraft according to the format.

14. The method of claim 11, wherein the executing further comprises:

determining, determining, by the voice router, a format for instructing the at least one subsystem to execute the command using the distribution model; and

transmitting, by the voice router, the instruction to execute the command to the at least one subsystem of the aircraft.

15. A voice router, comprising:

an interface configured to be coupled to a microphone and a plurality of subsystems of an aircraft; and

a processor coupled to the interface, the processor configured to

receive, from the microphone, voice command audio data;

convert, using an avionic language model, the voice command audio data into voice command text data;

determine, using a distribution model, whether a command corresponding to the voice command text data can be executed;

transmitting, to at least one of the plurality of subsystems, instructions to execute the command when the voice router determines that the command can be executed; and

providing, using the output system, feedback when the command is executed.

16. The voice router of claim 15, wherein the voice router is further configured to determine whether a command corresponding to the voice command text data can be executed by:

evaluating a rule corresponding to the command, wherein the rule is defined in the distribution model.

17. The voice router of claim 16, wherein the voice router is further configured to determine whether a command corresponding to the voice command text data can be executed by:

requesting data for evaluating the rule from at least one of the plurality of subsystems.

18. The voice router of claim 15, wherein the distribution model includes rules for whether the command corresponding to the voice command text data can be executed and procedures for executing the command.

19. The voice router of claim 15, wherein the avionic language model defines vocabulary, grammar and command parameters for a plurality of voice commands.

20. The voice router of claim 19, wherein the converting the voice command audio data into voice command text data further comprises:

performing speech recognition upon the voice command audio data; and

determining the voice command text data based upon an output of the speech recognition and the vocabulary, grammar and command parameters for the plurality of voice commands.