Smart circular audio buffer

Patent metadata

Field	Value
Publication number	US-9633669-B2
Application number	US-201314016403-A
Country	US
Kind code	B2
Filing date	Sep 3, 2013
Priority date	Sep 3, 2013
Publication date	Apr 25, 2017
Grant date	Apr 25, 2017

Abstract

An audio buffer is used to capture audio in anticipation of a user command to do so. Sensors and processor activity may be monitored, looking for indicia suggesting that the user command may be forthcoming. Upon detecting such indicia, a circular buffer is activated. Audio correction may be applied to the audio stored in the circular buffer. After receiving the user command instructing the device to process or record audio, at least a portion of the audio that was stored in the buffer before the command is combined with audio received after the command. The combined audio may then be processed, transmitted or stored.

First claim

What is claimed is:

1. A method of buffering audio on an electronic device, comprising:
detecting, at a first time, a first indication of impending device activity, the indicator comprising one or more of an activation of an application that processes audio, a change in incident light intensity, a visual recognition of motion, a visual recognition of a user in proximity to the electronic device, visual recognition of a face, a finger proximal to a touch-sensitive display screen, movement of the electronic device, ambient sound, speech, or recognition of a particular speaker;
receiving, starting at a second time after the first time, audio corresponding to an utterance;
storing audio data corresponding to the audio in a circular buffer, based at least in part on detecting the first indication;
receiving, at a third time after the second time, a second indication to process audio; and
in response to receiving the second indication:
combining, into combined audio data, at least a portion of the audio data corresponding to the utterance and stored in the circular buffer prior to receiving the second indication with further audio data corresponding to further audio received after receiving the second indication; and
sending the combined audio data for processing.

2. The method of claim 1 , further comprising generating the second indication in response to detecting a pressing of a physical button, a pressing of a virtual button provided via a graphical user interface, or a command gesture.

3. The method of claim 1 , further comprising:
calculating an audio correction to be applied to the received audio, in response to detecting the first indication and before receiving the second indication; and
applying the audio correction to audio data received after the second indication.

4. The method of claim 3 , wherein the audio correction comprises one or more of channel normalization or noise reduction.

5. A computing device, comprising:
at least one processor;
a memory device including instructions operable to be executed by the at least one processor to perform a set of actions, configuring the at least one processor to:
detect, at a first time, an indicator of impending device activity;
receive, starting at a second time after the first time, audio corresponding to an utterance;
store audio data corresponding to the audio in a first circular buffer, based at least in part on detecting the indicator;
receive, at a third time after the second time, a signal to process audio; and
in response to receipt of the signal:
combine, into combined audio data, at least a portion of the audio data corresponding to the utterance and stored in the first circular buffer prior to receipt of the signal with further audio data corresponding to further audio received after receipt of the signal; and
send the combined audio data for processing.

6. The computing device of claim 5 , wherein the instructions configuring the at least one processor to detect the indicator of impending device activity configure the at least one processor to detect the indicator of impending device activity based at least in part on output from sensors coupled to said at least one processor.

7. The computing device of claim 6 , wherein the indicator comprises one or more of an activation of an application that processes audio, a change in incident light intensity, a visual recognition of motion, a visual recognition of a user in proximity to the computing device, visual recognition of a face, a finger proximal to a touch-sensitive display screen, movement of the computing device, an ambient sound, speech, or recognition of a particular speaker.

8. The computing device of claim 5 , further comprising instructions further configuring the at least one processor to generate the signal to process audio in response to detection of a pressing of a physical button, a pressing of a virtual button provided via a graphical user interface of the device, or a gesture.

9. The computing device of claim 5 , further comprising instructions configuring the at least one processor to:
calculate an audio correction, prior to receipt of the signal to process audio; and
apply the audio correction to the further audio data.

10. The computing device of claim 9 , further comprising instructions configuring the at least one processor to:
calculate the audio correction based at least in part on second audio data stored in a second circular buffer; and
apply the audio correction to the audio data stored in the first circular buffer.

11. The computing device of claim 9 , wherein the audio correction comprises one or more of channel normalization or noise reduction.

12. The computing device of claim 5 , further comprising instructions configuring the at least one processor to:
recognize a pattern of device activity relating to utilization of captured audio based at least in part on a user history; and
compare at least the detected indicator of impending device activity and other data relating to occurrence of the indicator with the recognized pattern,
wherein activating the first circular buffer is further based at least in part on the comparison.

13. A non-transitory computer-readable storage medium storing processor-executable instructions for controlling a computing device, comprising:
program code to detect, at a first time, an indicator of impending device activity;
program code to receive, starting at a second time after the first time, audio corresponding to an utterance;
program code to store audio data corresponding to the audio in a first circular buffer, based at least in part on detecting the indicator;
program code to receive, at a third time after the second time, a signal to process audio; and
program code to, in response to receipt of the signal:
combine, into combined audio data, at least a portion of the audio data corresponding to the utterance and stored in the first circular buffer prior to receipt of the signal with further audio data corresponding to further audio received after receipt of the signal; and
send the combined audio data for processing.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the program code to detect the indicator of impending device activity is based at least in part on output from sensors of the computing device.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the indicator comprises one or more of an activation of an application that processes audio, a change in incident light intensity, a visual recognition of motion, a visual recognition of a user in proximity to the computing device, visual recognition of a face, a finger proximal to a touch-sensitive display screen, movement of the computing device, an ambient sound, speech, or recognition of a particular speaker.

16. The non-transitory computer-readable storage medium of claim 13 , further comprising program code to generate the signal to process audio in response to detection of a pressing of a physical button, a pressing of a virtual button provided via a graphical user interface of the computing device, or a gesture.

17. The non-transitory computer-readable storage medium of claim 13 , further comprising:
program code to calculate an audio correction, prior to receipt of the signal to process or record audio; and
program code to apply the audio correction to the further audio data.

18. The non-transitory computer-readable storage medium of claim 17 , wherein:
the program code to calculate the audio correction is based at leas

Assignees

• Amazon Tech Inc

Inventors

• Salvador Stan Weidner
• Schaaf Thomas

Classifications

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G06F3/16

  Sound input; Sound output (speech processing G10L) · CPC title

• G06F3/165

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title

• G06F40/55

  Rule-based translation · CPC title