Audio cancellation for voice recognition

1. A method of audio cancellation comprising:

machine-generating an audio cue at a first time;

playing the audio cue through a sound system in a sound environment, wherein the audio cue is detectable over background noise in the sound environment;

recording sound in an audio buffer using a microphone, the recording including the audio cue recorded at a second time;

detecting the audio cue in the recording from the audio buffer over the background noise in the sound environment;

determining a time delay between the first time of the generation of the audio cue and the second time that the audio cue was recorded in the recording in the audio buffer; and using the time delay to cancel audio from the sound system from subsequent recordings.

2. The method of claim 1 , wherein the audio cue has a first root mean square (RMS) higher than a second RMS associated with the background noise.

3. The method of claim 1 , wherein the audio cue has a strong attack of less than 100 milliseconds.

4. The method of claim 2 , wherein the audio cue comprises two or more frequencies.

5. The method of claim 1 , wherein the audio cue emanates from a snare drum.

6. The method of claim 2 , wherein the background noise is a person talking.

7. The method of claim 2 , wherein the background noise is associated with an operation of a motor vehicle or a room or building where the sound system is located.

8. The method of claim 2 , wherein the background noise emanates from an engine, a home appliance, a television, animal noises, wind noise, or traffic.

9. The method of claim 1 , wherein the audio cue comprises a plurality of signals, each signal played at a different time.

10. The method of claim 9 , wherein the time that the audio cue is detected in the recording occurs is when a peak-to-RMS ratio crosses a predetermined threshold.

11. The method of claim 10 , wherein the predetermined threshold is 30 dB.

12. The method of claim 11 , wherein the audio cue represents two or more signals, and wherein the method further comprises: averaging the time difference associated with the two or more signals.

13. A media playback system comprising:

a sound system including a media playback device and an audio output device, the media playback device operable to generate a media content signal, and the audio output device configured to play media content using the media content signal; and

wherein the sound system is configured to:

generate an audio cue using the media playback device at a first time;

transmit the audio cue to the audio output device;

play the audio cue through the audio output device;

record sound in an audio buffer using the media playback device, the recording including the audio cue recorded at a second time;

detect the audio cue in the recording from the audio buffer by determining that a peak-to-RMS ratio of the audio cue reaches or crosses a threshold;

determine a time delay between the first time of the generation of the audio cue and the second time that the audio cue was recorded in the recording in the audio buffer; and

play audio content through the audio output device;

receive a user command;

record the user command with the audio content;

determine which audio content has been recorded based on the time delay; and

filter the determined audio content to extract the user command from the recording of the user command with the audio content.

14. The media playback system of claim 13 , wherein the media playback device is paired with the audio output device via a wireless communication network, such as BLUETOOTH®.

15. The media playback system of claim 13 , wherein the sound system is configured to:

generate a second audio cue and playing the second audio cue through the sound system;

record sound in the audio buffer using the microphone, the recording including the second audio cue;

detect the second audio cue in the recording from the audio buffer by determining that a second peak-to-RMS ratio of the second audio cue crosses the threshold;

determine a second time delay between the generation of the second audio cue and a time that the second audio cue was recorded in the recording in the audio buffer;

determine a difference between the time delay and the second time delay;

determine whether the difference is within a threshold range;

when determined that the difference is within the threshold range, continue to use the time delay to cancel audio from the sound system from subsequent recordings; and

when determined that the difference is not within the threshold range, use the second time delay to cancel audio from subsequent recordings.

16. A method comprising:

generate an audio cue using a media playback device at a first time;

transmit the audio cue to an audio output device;

play the audio cue through the audio output device;

record sound in an audio buffer using the media playback device, the recording including the audio cue recorded at a second time;

detect the audio cue in the recording from the audio buffer by determining that a difference between a peak amplitude of the audio cue and a RMS of background noise, recorded with the audio cue, crosses a threshold;

determine a time delay between the first time of the generation of the audio cue and the second time that the audio cue was recorded in the recording in the audio buffer;

play audio content through the audio output device;

receive a user command;

record the user command with the audio content being played by the media playback device when the user command was received;

determine which audio content has been recorded based on the time delay; and

filter the determined audio content to extract the user command from the recording of the user command with the audio content.

17. The method of claim 16 , wherein the audio cue has a strong attack of less than 100 milliseconds.

18. The method of claim 16 , wherein the audio cue comprises two or more frequencies.

19. The method of claim 16 , wherein the audio cue mimics a sound that emanates from a snare drum.

20. The method of claim 16 , wherein the background noise is one or more of: a person talking, associated with an operation of a motor vehicle where the media playback device is located, associated with a room where the media playback device is located, associated with a building where the media playback device is located, emanates from an engine, emanates from a home appliance, emanates from a television, emanates from animal noises, emanates from wind noise, and/or emanates from traffic.