SYSTEM AND METHOD TO DISTINGUISH SOURCES IN A MULTIPLE AUDIO SOURCE ENVIRONMENT

• US 20170287500A1
• Filed: 04/04/2016
• Published: 10/05/2017
• Est. Priority Date: 04/04/2016
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: De Mers, Robert E., Dopilka, David J.
• Granted Patent: US 11,138,987 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 19/018 Audio watermarking, i.e. embedding inaudible data in the audio signal
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/028 using properties of sound source
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

A system and method capable of distinguishing sources in a multiple source environment is provided. The system receives an audio signal comprising an audio tag, a desired audio signal and an undesired audio signal. Based on the audio tag, the system eliminates the undesired audio signal and identifies an intended command in the desired audio signal. The system generates a command for an external device based on the intended command.

Claims

1. An audio system, comprising:

a memory device comprising a speech recognition algorithm and audio tags;

a processor coupled to the memory device, a source of undesired audio signal and a source of desired audio signal, the processor configured to

(i) receive an audio signal comprising (a) an undesired audio signal from the source of undesired audio, (b) a desired audio signal from the source of desired audio signal, the source of the undesired audio signal and the source of the desired audio signal being separate, and (c) an audio tag associated with one of the undesired audio signal or the desired audio signal,

and

(ii) based on the audio tag, eliminate the undesired audio signal from the audio signal prior to using the speech recognition algorithm to identify an intended command from the audio signal with the undesired audio signal eliminated.

2. The audio system of claim 1, wherein the audio tag is an externally created audio tag (ECT).

3. The audio system of claim 2, wherein the processor is further configured to (i) command a source of ECT to add the ECT to the source of the undesired audio signal, and (ii) create an association between the ECT and the source of undesired audio signal and store the association in the memory device.

5. The audio system of claim 1, further comprising a source of the desired audio signal coupled to the processor, and wherein the audio tag is a naturally occurring tag (NT), and

the processor is further configured to process the audio signal from the source of the desired audio signal to identify the naturally occurring audio tag (NT) unique to the source of desired audio signal, create an association between the NT and the source of the desired audio signal, and store the association in the memory device.

6. The audio system of claim 5, wherein the processor is further configured to process the audio signal to (i) identify a naturally occurring audio tag therein, and (ii) associate the naturally occurring audio tag with the source of desired audio signal.

7. The audio system of claim 6, further comprising a sensor coupled to the processor and the source of desired audio signal.

9. The audio system of claim 7, wherein the processor is further configured to:

audio process the desired audio signal to identify therein an intended device associated with the intended command; and

generate a command that is responsive to the intended command and intended device.

10. The audio system of claim 3, wherein the ECT comprises at least one signal characteristic from the set of signal characteristics including:

analog, digital, continuous, pulsed, patterned, audible, sub audible and super audible.

21. The audio system of claim 1, wherein the processor is further configured to distinguish among the source of undesired audio signal and the source of desired audio signal when audio transmissions from the source of undesired audio signal and audio transmissions from the source of desired audio signal are transmitted in one from the set of concurrent, overlapping, and sequential order.

4. (canceled)

8. (canceled)

11. An audio processing method, the method comprising:

detecting, by an audio capture device, audio transmissions comprising (i) an undesired audio signal from a source of undesired audio, and (ii) a desired audio signal from a source of desired audio signal, the source of the undesired audio signal and the source of the desired audio signal being separate;

converting, by the audio capture device, the audio transmissions into a collective audio signal comprising an audio tag, the desired audio signal and the undesired audio signal;

receiving, at a processor, the audio signal comprising the audio tag, desired audio signal and undesired audio signal;

processing the audio signal, using speech recognition algorithms stored in a memory device;

eliminating the undesired audio signal from the audio signal based on the audio tag; and

generating a command for an external device using the audio signal with the undesired audio signal eliminated.

12. The audio processing method of claim 11, further comprising determining, by the processor, that it has access to the source of the undesired audio signal.

13. The audio processing method of claim 12, wherein the audio tag is an externally created audio tag (ECT), and further comprising, responsive to the processor determining that it has access to the source of the undesired audio signal:

commanding a source of ECT to add the ECT to the undesired audio signal, and

creating an association between the ECT and the source of undesired audio signal and storing the association in the memory device.

14. The audio processing method of claim 11, further comprising determining, by the processor, that it has access to the source of the desired audio signal.

15. The audio processing method of claim 14, wherein the audio tag is a naturally occurring tag (NT), and further comprising, responsive to the processor determining that it has access to the source of the desired audio signal:

processing the desired audio signal to identify the naturally occurring tag (NT) therein, and

creating an association between the NT and the source of the desired audio signal and storing the association in the memory device.

16. The audio processing method of claim 11, wherein, upon determining that it does not have access to any sources of the audio signal, the processor is further configured to process the audio signal to

(i) identify a naturally occurring audio tag in the undesired audio signal and associate the naturally occurring audio tag in the undesired audio signal with a source of undesired audio signal, or

(ii) identify a naturally occurring audio tag in the desired audio signal and associate the naturally occurring audio tag in the desired audio signal with a source of desired audio signal.

22. The audio processing method of claim 11, further comprising distinguishing among the source of undesired audio signal and the source of desired audio signal when audio transmissions from the source of undesired audio signal and audio transmissions from the source of desired audio signal are transmitted in one from the set of concurrent, overlapping, and sequential order.

17. An audio system, comprising:

a memory device comprising speech recognition algorithms;

a processor coupled to the memory device, the processor configured to

(i) receive an audio signal comprising (a) an undesired audio signal from a source of undesired audio, (b) a desired audio signal from a source of desired audio signal, the source of the undesired audio signal and the source of the desired audio signal being separate, and (c) an audio tag,

(ii) identify the audio tag in the audio signal, and

(iii) eliminate the undesired audio signal from the audio signal prior to processing the audio signal and identifying a command therein.

18. The audio system of claim 17, wherein the processor is further configured to:

command a source of externally created audio tag (ECT) to add an ECT to the source of the undesired audio signal, and

store an association between the ECT and the source of the undesired audio signal in the memory device.

19. The audio system of claim 18, wherein the processor is further configured to:

process the desired audio signal to identify a naturally occurring tag therein, and

store an association between the naturally occurring tag and the source of the desired audio signal in the memory device.

20. The audio system of claim 19, further comprising:

a user interface for providing an enable signal; and

wherein the processor is further configured to generate a command for an external device based on the intended command when the enable signal is asserted.