Sound signature database for initialization of noise reduction in recordings

• US 10,178,474 B2
• Filed: 04/21/2015
• Issued: 01/08/2019
• Est. Priority Date: 04/21/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Klimanis, Gints Valdis
• Primary Examiner(s): Kim, Paul S
• Assistant Examiner(s): Odunukwe, Ubachukwu
• Application Number:
  US14/692,581
• Publication Number:
  US 20160316293A1
• Time in Patent Office: 1,358 Days
• Field of Search: 381 711, 381 712, 381 713, 381 714, 381103, 381 943, 381 56, 381 77, 704233
• CPC Class Codes: G10K 2210/105 Appliances, e.g. washing machines or dishwashers
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: G10L 25/54 for retrieval
• CPC Class Codes: H04L 12/2823 Reporting information sensed by appliance or service execution status of appliance services in a home automation network device-related reporting H04L43/065; arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom H04Q9/00
• CPC Class Codes: H04R 1/028 associated with devices performing functions other than acoustics, e.g. electric candles
• CPC Class Codes: H04R 2410/05 Noise reduction with a separate noise microphone
• CPC Class Codes: H04R 3/00 Circuits for transducers , loudspeakers or microphones

Abstract

A smart-home device may include a recording device configured to record sound during a first time interval and a memory device comprising a plurality of stored sound profiles. The smart-home device may also include a processing system configured to receive an environmental input, select a stored sound profile from the plurality of stored sound profiles based on the environmental input, and perform a noise-cancelation routine on the sound recorded during the first time interval. The stored sound profile may be used as an initial background noise profile for the noise-cancelation routine.

Claims

1. A smart-home device comprising:

a recording device configured to record sound during a first time interval;

a memory device comprising a plurality of stored sound profiles;

a processing system configured to;

receive a communication transmitted from a household appliance indicating that the household appliance is operating;

in response to receiving the communication transmitted from the household appliance, select a stored sound profile from the plurality of stored sound profiles based on a sound made by the household appliance while the household appliance is operating; and

perform a noise-cancellation routine on the sound recorded during the first time interval, wherein the stored sound profile is used as an initial background noise profile for the noise-cancelation routine.

2. The smart-home device of claim 1 wherein the smart-home device comprises a hazard detector, the hazard detector comprising:

a smoke detector; and

a carbon monoxide detector.

3. The smart-home device of claim 1 wherein the smart-home device comprises a thermostat, the thermostat comprising:

a temperature sensor; and

a motion sensor.

4. The smart-home device of claim 1, further comprising a network interface in communication with a remote server.

5. The smart-home device of claim 4, wherein the processing system is further configured to:

receive an environmental input;

send the environmental input to the remote server through the network interface;

receive a second stored sound profile through the network interface from the remote server, wherein the remote server selected the second stored sound profile based on the environmental input; and

perform the noise-cancellation routine on sound recorded during a second time interval, wherein the second stored sound profile is used as an initial background noise profile for the noise-cancellation routine.

6. The smart-home device of claim 4, wherein the processing system is further configured to:

record a new sound profile using a microphone; and

send the new sound profile to the remote server through the network interface.

7. The smart-home device of claim 4, wherein:

the smart-home device is in communication through the network interface with the household appliance within a same home; and

the communication is received from the household appliance through the network interface.

8. The smart-home device of claim 1, wherein the stored sound profile is recorded by a second smart-home device within the same home and transmitted from the second smart-home device to the smart-home device.

9. A method of selecting an initial background noise for a noise-cancelation routine in a smart-home device, the method comprising:

receiving, by the smart-home device, a communication from a household appliance indicating that the household appliance is operating;

selecting, using a processor on the smart-home device, and in response to receiving the communication from the household appliance, a stored sound profile from a plurality of stored sound profiles, wherein the stored sound profile is selected based on a sound made by the household appliance while the household appliance is operating; and

performing the noise-cancelation routine on sound received through a microphone of the smart-home device, wherein the noise-cancelation routine is performed using the stored sound profile as an initial background noise for the noise-cancelation routine.

10. The method of claim 9, wherein the sound received through the microphone of the smart-home device has a duration of less than 10 seconds.

11. The method of claim 9, wherein the noise-cancellation routine uses the initial background noise as a starting point for a convergence algorithm.

12. The method of claim 11, further comprising:

determining that a second stored sound profile will cause the convergence algorithm to converge faster than the stored sound profile; and

providing the second stored sound profile to the noise-cancellation routine.

13. The method of claim 9, further comprising, during a learning interval, building the plurality of stored sound profiles by:

detecting a time interval during which a steady-state background noise is present;

recording the steady-state background noise; and

recording characteristics of the occurrence of the steady-state background noise.

14. A non-transitory memory device comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving, by the one or more processors, a communication transmitted from a household appliance indicating that the household appliance is operating;

selecting, using the one or more processors, and in response to receiving the communication transmitted from the household appliance, a stored sound profile from a plurality of stored sound profiles, wherein the stored sound profile is selected based on a sound made by the household appliance while the household appliance is operating; and

performing a noise-cancelation routine on a received sound, wherein the noise-cancellation routine is performed using the stored sound profile as an initial background noise for the noise-cancelation routine.

15. The non-transitory memory device of claim 14, wherein the stored sound profile is associated with sound emitted by a household appliance during operation.

16. The non-transitory memory device of claim 14, wherein the received sound comprises a voice command.

17. The non-transitory memory device of claim 14, wherein the noise-cancelation routine is performed on the received sound in real-time.