Spatial audio database based noise discrimination

1. A method for spatial audio database based noise discrimination, comprising:

capturing a sound by a plurality of microphones in an area;

segregating the sound into a plurality of signals, wherein each signal corresponds to a respective portion of the area;

comparing the plurality of signals to a spatial audio database of a plurality of portions of the area in response to identifying a confidence level of an instruction, based on a speech command issued by a user, of the captured sound being below a threshold level;

discriminating a speech command and a background noise from the captured sound based on the comparison to the spatial audio database; and

determining an instruction based on the discriminated speech command.

2. The method of claim 1 , wherein the confidence level includes a percentage that corresponds to a likelihood a determined instruction correctly corresponds to the discriminated speech command.

3. The method of claim 1 , wherein discriminating the speech command from background noise includes discriminating based on a threshold comparison between a user's voice and a background noise stored in the spatial audio database.

4. The method of claim 1 , including capturing sounds in the area for the spatial audio database during an installation of the plurality of microphones.

5. The method of claim 4 , including updating the spatial audio data base with a new sound captured in the area.

6. A non-transitory computer readable medium, comprising instructions executable by a processing resource to cause a computing device to:

create a spatial audio database of a plurality of portions of an area;

receive a sound segregated into a plurality of signals, wherein the sound is captured in the area and wherein each respective signal corresponds to a different portion of the area;

compare the plurality of signals to the spatial audio database of a plurality of portions of the area in response to identifying a confidence level of an instruction, based on a speech command issued by a user, of the captured sound being below a threshold level;

discriminate a speech command from a background noise based on the comparison of the plurality of signals to the spatial audio database;

determine an instruction based on the discriminated speech command; and

send the instruction to a sound recognition device in the area to perform the command.

7. The medium of claim 6 , wherein the instructions to create the spatial audio database include instructions executable by the processing resource to:

use a plurality of sounds received from a plurality of microphones associated with the sound recognition device to create the spatial audio database.

8. The medium of claim 7 , including instructions executable by the processing resource to segregate each of the plurality of sounds into the plurality of signals.

9. The medium of claim 7 , wherein the instructions to create the spatial audio database include instructions executable by the processing resource to process the plurality of signals to recognize identification characteristics of the sounds captured.

10. The medium of claim 6 , wherein the instructions to compare the received sound to the spatial audio database include instructions executable by the processing resource to identify if the background noise exists in the plurality of signals based on the comparison.

11. The medium of claim 6 , wherein the instructions to compare the received sound includes instructions executable by the processing resource to compare the plurality of signals to a signal reception threshold to confirm a type of background noise present and/or the background noise mixed with the speech command.

12. The medium of claim 6 , wherein the instructions to discriminate the speech command include instructions executable by the processing resource to use a subtraction technique to suppress the background noise from the speech command.

13. The medium of claim 6 , wherein instructions to discriminate the speech command include instructions executable by the processing resource to discriminate the speech command from the background noise based on a threshold comparison of the plurality of signals and a sound stored in the spatial audio database.

14. A system, comprising:

an array of microphones to capture sounds from a plurality of beam directions and a plurality of beam widths;

a digital signal processor to segregate each captured sound into a plurality of signals wherein each respective signal corresponds to a different angular portion of the area;

an adaptive noise discrimination component to:

create a spatial audio database using the segregated plurality of signals corresponding to different angular portions of the area of each captured sound;

compare a subsequently captured sound to the spatial audio database of a plurality of portions of the area in response to identifying a confidence level of an instruction, based on a speech command issued by a user, of the captured sound being below a threshold level; and

discriminate a speech command from a background noise based on the comparison of the subsequently captured sound to the spatial audio database; and

an automatic speech recognition engine to analyze the discriminated speech command at the defined beam direction and defined beam width.

15. The system of claim 14 , wherein the adaptive noise discrimination component:

in response to the comparison resulting in an identified background noise, discriminates the speech command from background noise using a spatial-temporal filter; and

in response to the comparison resulting in no identified background noise, sends the speech command to the automatic speech recognition engine.

16. The system of claim 14 , wherein the automatic speech recognition engine sends feedback to the digital signal processor, including at least one of:

an alternate beam angle from the plurality of beam angles; and

an alternate beam width from the plurality of beam widths.

17. The system of claim 14 , wherein the array of microphones, the digital signal processor, and the automatic speech recognition engine are included in a sound recognition device.

18. The system of claim 14 , wherein:

the area of microphones and the digital speech processor are included in a sound recognition device; and

the automatic speech recognition engine is communicatively coupled to the sound recognition device via a network.

19. The system of claim 14 , wherein:

the array of microphones are included in a sound recognition device; and

the digital speech processor and the automatic speech recognition engine are communicatively coupled to the sound recognition device via a network.