Dynamic and self-adjusting microphone gain for voice-enabled devices

1. A method, comprising:

receiving, by a voice-enabled device comprising a processor and from a microphone, a first input comprising environmental audio;

determining, by the voice-enabled device, a level of the environmental audio;

determining, by the voice-enabled device, a first gain-adjust value based on the environmental audio;

adjusting, by the voice-enabled device, a gain of the microphone by the first gain-adjust value;

receiving, by the voice-enabled device, from the microphone, a second input comprising a human voice;

determining, by the voice-enabled device, a level of clarity of the human voice in response to adjusting the first gain-adjust value;

determining, by the voice-enabled device, a second gain-adjust value to increase the level of clarity of the human voice; and

adjusting, by the voice-enabled device, the gain of the microphone by the second gain-adjust value.

2. The method of claim 1 , wherein determining the level of the environmental audio repeatedly occurs according to a time-interval.

3. The method of claim 2 , wherein the time-interval is adjustable according to a measurement of at least one of an amount or a frequency of recent change in the environmental audio in a defined past period of time.

4. The method of claim 1 , further comprising:

determining, by the voice-enabled device, a noise level, wherein the noise level comprises a difference between the level of the environmental audio and a predetermined threshold audio level representative of what has been designated a quiet mode for a room in which the environmental audio is minimized or substantially minimized.

5. The method of claim 4 , further comprising:

determining, by the voice-enabled device, a prior adjust value, wherein the prior adjust value comprises a difference between the noise level and a current gain value.

6. The method of claim 5 , wherein determining the first gain-adjust value comprises a combination of a gain value required to distinguish voice information from the environmental audio and the prior adjust value.

7. The method of claim 1 , wherein the microphone comprises a pre-amplifier, and wherein adjusting the gain of the microphone comprises adjusting the pre-amplifier.

8. The method of claim 1 , wherein adjusting the gain comprises lowering the gain in response to a determination that the level of the environmental audio is below a threshold value.

9. The method of claim 1 , wherein adjusting the gain comprising increasing the gain in response to a determination that the level of the environmental audio is above a threshold value.

10. The method of claim 1 , wherein the second input comprising the human voice further comprises a voice command to execute a function of the voice-enabled device.

11. A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor of a device for which voice input is supported, facilitate performance of operations, comprising:

receiving, from a receiver comprising a pre-amplifier, a first signal comprising environmental audio;

determining a level of the environmental audio;

determining a first gain-adjust value based on the environmental audio;

adjusting a gain of the pre-amplifier, by the first gain-adjust value;

receiving, from the receiver, a second signal comprising a voice;

determining a level of clarity of the voice in response to adjusting the first gain-adjust value;

determining a second gain-adjust value that increases the level of clarity of the voice; and

adjusting the gain of the pre-amplifier by the second gain-adjust value.

12. The non-transitory machine-readable medium, of claim 11 , wherein the operations further comprise:

a filter, wherein the filter suppresses a frequency range of the first signal comprising the environmental audio.

13. The non-transitory machine-readable medium of claim 12 , wherein the frequency range comprises background noise.

14. The non-transitory machine-readable medium of claim 12 , wherein the frequency range comprises a voice not registered with the device.

15. The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise:

determining whether the second signal comprises a voice registered with the voice-activated device; and

adjusting the gain of the pre-amplifier to amplify a frequency range associated with the voice.

16. The non-transitory machine-readable medium of claim 15 , wherein the voice registered with the device is a first voice,

wherein adjusting the gain of the pre-amplifier to amplify the first voice comprises not amplifying a second frequency range associated with a second voice, and

wherein the second voice is not registered with the device.

17. A voice-enabled device, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:

receiving, from an audio receiver, a signal comprising voice information and ambient noise;

filtering the signal with a bandpass filter of the voice-enabled device, resulting in a filtered signal;

determining a first gain-adjustment value for the filtered signal;

applying the first gain-adjustment value to an operational amplifier of the voice-enabled device, whereby the operational amplifier amplifies the signal;

determining a level of clarity of the voice information in response to applying the first gain-adjustment value;

determining, a second gain-adjustment value to increase the level of clarity of the voice information; and

applying the second gain-adjustment value to the operational amplifier.

18. The voice-enabled device of claim 17 , wherein the first gain-adjustment value is only applied to a frequency range determined to be associated with the voice information.

19. The voice-enabled device of claim 17 , wherein the voice-enabled device is battery-powered.

20. The voice-enabled device of claim 17 , wherein the operations occur repeatedly according to an interval, and wherein the voice-enabled device is responsive to changes in the signal from interval to interval.