Audio command adaptive processing system and method

Patent metadata

Field	Value
Publication number	US-10276180-B2
Application number	US-201414336181-A
Country	US
Kind code	B2
Filing date	Jul 21, 2014
Priority date	Jul 21, 2014
Publication date	Apr 30, 2019
Grant date	Apr 30, 2019

Abstract

A system and method are provided for adaptively processing audio commands supplied by a user in an aircraft cabin, and includes receiving ambient noise in the aircraft cabin via one or more audio input device, sampling, with a processor, the received ambient noise, and analyzing, in the processor, the sampled ambient noise and, based on the analysis, selecting one or more filter functions and adjusting one or more filter parameters associated with the one or more selected filter functions. Audio and ambient noise are selectively received via the one or more audio input devices, and are filtered, through the selected one or more filter functions, to thereby supply filtered audio.

First claim

What is claimed is:

1. A method for adaptively processing audio commands supplied by a user in an aircraft cabin, comprising the steps of:
receiving ambient noise in the aircraft cabin via a first audio input device;
continuously sampling, with a processor, the ambient noise received via the first audio input device;
determining, in the processor, an aircraft type and a location within the determined aircraft type;
continuously analyzing, in the processor, the sampled ambient noise and, based on the continuous analysis, the determined aircraft type and, the determined location within the determined aircraft type, selecting one or more filter functions and adjusting one or more filter parameters associated with the one or more selected filter functions;
selectively receiving audio and ambient noise via a second audio input device; and
filtering, through the selected one or more filter functions, the audio and ambient noise received via the second audio input device, to thereby supply filtered audio.

2. The method of claim 1 , wherein:
the step of continuously analyzing comprises continuously analyzing the sampled ambient noise for power in specific frequency bands; and
the step of selecting the one or more filter types and adjusting the one or more filter parameters is based at least in part on the power in one or more of the specific frequency bands.

3. The method of claim 1 , further comprising:
analyzing the audio received by the second audio input devices to determine when it includes human speech, and
supplying the filtered audio to a speech recognizer when it is determined that the audio received by the second audio input device includes human speech,
wherein the speech recognizer supplies one or more recognized words.

4. The method of claim 3 , further comprising:
determining when a number of recognized words exceeds a predetermined number within a predetermined time period; and
re-initializing the one or more filter functions when is determined that the number of recognized words exceeds the predetermined number within the predetermined time period.

5. The method of claim 3 , further comprising:
analyzing the one or more recognized words to discern an intent thereof; and
re-initializing the one or more filter functions when the intent cannot be discerned.

6. The method of claim 1 , further comprising:
determining a position of the user within the aircraft cabin;
at least selectively generating an aircraft cabin control command based on the one or more recognized words and on the position of the user.

7. The method of claim 1 , further comprising:
selectively rendering, on a display device, one or more user interfaces based on the one or more recognized words.

8. A system for adaptively processing audio commands supplied by a user in an aircraft cabin, comprising:
a first audio input device adapted to receive ambient noise in the aircraft cabin and supply ambient noise signals representative thereof;
a second audio input device adapted to at least selectively receive audio and ambient noise and supply audio signals representative thereof; and
a processing system in operable communication with the first and second audio input devices, the processing system configured to:
(i) receive data representative of an aircraft type,
(ii) receive data representative of a location within the determined aircraft type,
(iii) continuously sample and analyze the received ambient noise and, based on the continuous analysis, the aircraft type, and the location within the aircraft type, implement one or more filter functions and adjust one or more filter parameters associated with the one or more selected filter functions, and
(iv) filter, through the selected one or more filter functions, the audio and ambient noise received by the second audio input device, to thereby supply filtered audio.

9. The system of claim 8 , wherein the processing system is further configured to:
continuously analyze the sampled ambient noise for power in specific frequency bands;
select the one or more filter types and adjust the one or more filter parameters based at least in part on the power in one or more of the specific frequency bands.

10. The system of claim 8 , wherein the processing system is further configured to:
implement a speech recognizer that supplies one or more recognized words;
analyze the audio supplied to second audio input device to determine when it includes human speech; and
process the filtered audio in the speech recognizer when it is determined that the audio supplied to the second audio input device includes human speech.

11. The system of claim 10 , wherein the processing system is further configured to:
determine when a number of recognized words exceeds a predetermined number within a predetermined time period; and
re-initialize the one or more filter functions when is determined that the number of recognized words exceeds the predetermined number within the predetermined time period.

12. The system of claim 11 , wherein the processing system is further configured to:
analyze the one or more recognized words to discern an intent thereof; and
re-initialize the one or more filter functions when the intent cannot be discerned.

13. The system of claim 10 , wherein the processing system is further configured to:
receive data representative of a position of the user within the aircraft cabin; and
at least selectively generate an aircraft cabin control command based on the one or more recognized words and on the position of the user.

14. The system of claim 10 , further comprising:
a display device in operable communication with the processing system,
wherein the processing system is further configured to selectively render, on the display device, one or more user interfaces based on the one or more recognized words.

15. A system for adaptively processing audio commands supplied by a user in an aircraft cabin, comprising:
a first audio input device adapted to receive ambient noise in the aircraft cabin and supply ambient noise signals representative thereof;
a second audio input device adapted to at least selectively receive audio and ambient noise and supply audio signals representative thereof; and
a processing system in operable communication with the first and second audio input devices, the processing system configured to:
(i) continuously sample and analyze the received ambient noise and, based on the continuous analysis, implement one or more filter functions and adjust one or more filter parameters associated with the one or more selected filter functions,
(ii) filter, through the selected one or more filter functions, the audio and ambient noise received by the second audio input device, to thereby supply filtered audio;
(iii) receive data representative of a position of the user within the aircraft cabin,
(iv) implement a speech recognizer that supplies one or more recognized words,
(v) analyze the audio supplied to second audio input device to determine when it includes human speech,
(vi) process the filtered audio in the speech recognizer when it is determined that the audio supplied to the second audio input device includes human speech, and
(vii) at least selectively generate an aircraft cabin control command based on the one or more recognized words and on the position of the user.

Assignees

• Honeywell Int Inc

Inventors

• Martinez Steven
• Mead Stephen
• Paulraj Vasantha Selvi

Classifications

• G10L2021/02165

  Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal · CPC title

• G10L21/0216 Primary

  characterised by the method used for estimating noise · CPC title

• B64C2220/00

  Active noise reduction systems · CPC title