Audio cancellation for voice recognition
An audio cancellation system includes a voice enabled computing system that is connected to an audio output device using a wired or wireless communication network. The voice enabled computing device can provide media content to a user and receive a voice command from the user. The connection between the voice enabled computing system and the audio output device introduces a time delay between the media content being generated at the voice enabled computing device and the media content being reproduced at the audio output device. The system operates to determine a calibration value adapted for the voice enabled computing system and the audio output device. The system uses the calibration value to filter the user's voice command from a recording of ambient sound including the media content, without requiring significant use of memory and computing resources.
1. A sound system comprising:
a media playback device configured to:
machine-generate an audio cue at a first time;
send an audio cue at a first time to an audio output device;
record sound in an audio buffer using a microphone, the recording including the audio cue recorded at a second time;
detect the audio cue in the recording from the audio buffer over the background noise in the sound environment;
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
use the time delay to cancel audio from the sound system from subsequent recordings; and
the audio output device configured to:
play media content using a media content signal;
receive the audio cue from the media playback device; and
play the audio cue.
2. The sound system 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 sound system of claim 1 , wherein the audio cue has a strong attack of less than 100 milliseconds.
4. The sound system of claim 1 , wherein the audio cue comprises two or more frequencies.
5. The sound system of claim 1 , wherein the audio cue is an emulated sound from a snare drum.
6. The sound system of claim 1 , wherein the background noise is a person talking.
7. The sound system of claim 1 , wherein the background noise is associated with an operation of a motor vehicle or is noise from a room or building where the sound system is located.
8. The sound system of claim 1 , wherein the background noise emanates from an engine, a home appliance, a television, an animal, wind noise, or traffic.
9. The sound system of claim 1 , wherein the audio cue represents a first signal sent at the first time and a second signal sent at a third time, and wherein the first time and the third time are different.
10. The sound system of claim 9 , wherein the media playback device is further configured to:
determine a first time delay associated with the first signal;
determine a second time delay associated with the second signal; and
average the first time delay and the second time delay associated with the first and second signals to determine the time delay.
11. The sound system of claim 1 , wherein the second time at which the audio cue is detected in the recording occurs when a peak-to-RMS ratio crosses a predetermined threshold.
12. The sound system of claim 11 , wherein the predetermined threshold is 30 decibels.
13. A media playback device comprising:
a processor;
a memory storing data instructions that, when executed by the processor, cause the media playback device to:
send an audio cue at a first time;
record sound in an audio buffer using a microphone, the recording including the audio cue recorded at a second time;
detect the audio cue in the recording from the audio buffer over the background noise in the sound environment;
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
use the time delay to cancel audio from the sound system from subsequent recordings.
14. The media playback device of claim 13 , wherein the audio cue has a first root mean square (RMS) higher than a second RMS associated with the background noise.
15. The media playback device of claim 14 , wherein the audio cue has a strong attack of less than 100 milliseconds.
16. The media playback device of claim 13 , wherein the audio cue comprises two or more frequencies.
17. The media playback device of claim 13 , wherein the audio cue represents a first signal sent at the first time and a second signal sent at a third time, and wherein the first time and the third time are different, and wherein the method further comprises:
determining a first time delay associated with the first signal;
determining a second time delay associated with the second signal; and
averaging the first time delay and the second time delay associated with the first and second signals to determine the time delay.
18. A non-transitory computer readable medium having stored thereon instructions, which when executed by a processor of a computing device, cause the computing device to:
send an audio cue at a first time;
record sound in an audio buffer using a microphone, the recording including the audio cue recorded at a second time;
detect the audio cue in the recording from the audio buffer over the background noise in the sound environment;
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
use the time delay to cancel audio from the sound system from subsequent recordings.
19. The non-transitory computer readable medium of claim 18 , wherein the audio cue has a first root mean square (RMS) higher than a second RMS associated with the background noise, and wherein the audio cue has a strong attack of less than 100 milliseconds.
20. The non-transitory computer readable medium of claim 18 , wherein the audio cue comprises two or more frequencies.