NOISE PROFILE DETERMINATION FOR VOICE-RELATED FEATURE

• US 20110166856A1
• Filed: 01/06/2010
• Published: 07/07/2011
• Est. Priority Date: 01/06/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Williams, Joseph M., Lindahl, Aram, Klimanis, Gints Valdis
• Granted Patent: US 8,600,743 B2
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2021/02163 Only one microphone
• CPC Class Codes: G10L 2021/02168 the estimation exclusively taking place during speech pauses
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

Systems, methods, and devices for noise profile determination for a voice-related feature of an electronic device are provided. In one example, an electronic device capable of such noise profile determination may include a microphone and data processing circuitry. When a voice-related feature of the electronic device is not in use, the microphone may obtain ambient sounds. The data processing circuitry may determine a noise profile based at least in part on the obtained ambient sounds. The noise profile may enable the data processing circuitry to at least partially filter other ambient sounds obtained when the voice-related feature of the electronic device is in use.

Claims

1. An electronic device comprising:

a microphone capable of obtaining ambient sounds when a user voice-related feature of the electronic device is not in use; and

data processing circuitry capable of determining a noise profile based at least in part on the ambient sounds, wherein the noise profile is configured to enable the data processing circuitry to at least partially filter other ambient sounds obtained when the user voice-related feature of the electronic device is in use.

2. The electronic device of claim 1, wherein the voice-related feature comprises a voice recognition feature;

a voice note recording feature;

or a video recording feature;

or any combination thereof.

3. The electronic device of claim 1, wherein the microphone is capable of periodically obtaining the ambient sounds when the user voice-related feature of the electronic device is not in use.

4. The electronic device of claim 1, wherein the microphone is capable of obtaining the ambient sounds when another user feature of the electronic device is in use.

5. The electronic device of claim 1, wherein the microphone is capable of obtaining the ambient sounds when an action indicative of an intent to use the user voice-related feature of the electronic device is undertaken.

6. The electronic device of claim 1, comprising memory capable of storing the noise profile after the noise profile is determined and recalling the noise profile when the user voice-related feature of the electronic device is in use.

7. A method comprising:

periodically activating a microphone associated with an electronic device when a voice-related feature of the electronic device is not in use;

obtaining ambient sounds using the microphone; and

determining a noise profile based at least in part on the ambient sounds using the electronic device, wherein the noise profile is configured to enable the electronic device to at least partially filter other ambient sounds obtained at a later time when the voice-related feature of the electronic device is in use.

8. The method of claim 7, wherein periodically activating the microphone comprises activating the microphone after a period of inactivity, wherein the period of inactivity is determined by the electronic device based at least in part on an operative mode of the electronic device;

a state of a power supply of the electronic device;

motion of the electronic device;

a variability of other noise profiles previously determined;

a location of the electronic device;

or a usage history of the voice-related feature of the electronic device;

or any combination thereof.

9. The method of claim 7, wherein the ambient sounds are obtained during a sampling period, wherein the sampling period is determined by the electronic device based at least in part on an error rate of the voice-related feature of the electronic device associated with the noise profile;

a convergence time associated with the determination of the noise profile;

a comparison of the obtained ambient sounds to previously-obtained ambient sounds;

or whether another noise profile based on other ambient sounds obtained in a similar context is stored on the electronic device;

or any combination thereof.

10. The method of claim 7, comprising assessing a current context of the electronic device to be stored in association with the noise profile, wherein assessing the current device context comprises determining a time from a clock of the electronic device;

a location from location-sensing circuitry of the electronic device;

an amount of ambient light from image-capture circuitry of the electronic device;

a motion of the electronic device from motion-sensing circuitry of the electronic device;

or a volume of the ambient sounds from the microphone;

or any combination thereof.

11. The method of claim 7, comprising storing the noise profile in a memory device when the voice-related feature of the electronic device is not in use and recalling the noise profile from the memory device when the voice-related feature of the electronic device is in use, obtaining a voice signal and the other ambient sounds using the microphone when the voice-related feature of the electronic device is in use, and at least partially filtering the other ambient sounds based at least in part on the noise profile using the electronic device when the voice-related feature of the electronic device is in use.

12. A system comprising:

a microphone capable of obtaining an audio signal that includes a voice and ambient sounds; and

an electronic device capable of receiving the audio signal, determining a current context of use of the electronic device, selecting a contextual noise profile based on the current context, and at least partially filtering the ambient sounds from the audio signal to obtain the voice.

13. The system of claim 12, wherein the microphone comprises a wireless headset;

a wired headset;

or a standalone microphone;

or any combination thereof.

14. The system of claim 12, wherein the contextual noise profile comprises a noise profile previously determined by the electronic device based at least in part on other ambient sounds obtained by the microphone during another context of use similar to the current context of use.

15. The system of claim 12, wherein the electronic device is capable of determining the current context of use based at least in part on a time from an internal clock of the electronic device;

a location from location-sensing circuitry of the electronic device;

an amount of ambient light from image-capture circuitry of the electronic device;

a motion of the electronic device from motion-sensing circuitry of the electronic device;

or a volume of the ambient sounds from the microphone;

or any combination thereof.

16. An electronic device comprising:

a microphone configured to obtain ambient sounds when a stimulus occurs before a voice-related feature of the electronic device has been activated; and

data processing circuitry configured to determine a noise profile based at least in part on the ambient sounds, wherein the noise profile is configured to enable the data processing circuitry to at least partially filter other ambient sounds obtained when the voice-related feature of the electronic device is active.

17. The electronic device of claim 16, wherein the microphone is configured to face away from a user of the electronic device when the electronic device is in use.

18. The electronic device of claim 16, wherein the stimulus comprises when an action indicative of an intent to use the voice-related feature of the electronic device is undertaken;

when another feature of the electronic device is activated;

when the electronic device is initialized;

when the electronic device senses a change in a current context of use;

or when a voice of a non-user is playing through a speaker of the electronic device while a telephone feature of the electronic device is in use;

or any combination thereof.

19. A method comprising:

receiving, into a processor, a first audio signal representative of ambient sounds obtained before voice recognition software on the processor has been selected to run on the processor; and

determining, using the processor, a noise profile based at least in part on the first audio signal before the voice recognition software on the processor has been selected to run on the processor, wherein the noise profile is configured to enable the processor to at least partially filter the ambient sounds from another audio signal.

20. The method of claim 19, comprising storing, onto a memory device, the noise profile and receiving, into the processor, a second audio signal representative of a voice and the ambient sounds and at least partially filtering, using the processor, the ambient sounds from the second audio signal to determine the voice.

21. The method of claim 19, comprising obtaining, using a microphone associated with the electronic device, the first audio signal before voice recognition software on the processor has been selected to run on the processor.

22. The method of claim 21, wherein the first audio signal is obtained after a regular period of microphone inactivity.

23. The method of claim 21, wherein the first audio signal is obtained after an irregular period of inactivity that ends when a stimulus occurs.