Background noise reduction in voice communication

Patent metadata

Field	Value
Publication number	US-2016198030-A1
Application number	US-201314377388-A
Country	US
Kind code	A1
Filing date	Jul 17, 2013
Priority date	Jul 17, 2013
Publication date	Jul 7, 2016
Grant date	—

Abstract

Technologies are generally described for a noise cancellation scheme for voice communications. In some examples a system configured to cancel background noise in voice communication may include a user device configured to capture a background sound; and a server configured to receive the background sound captured by the user device, identify a source of the background sound from among a plurality of predetermined sound sources, and generate a reference background sound based at least in part on the identified source.

First claim

1 . A system configured to cancel background noise in voice communication, the system comprising:
a user device configured to capture a background sound; and a server configured to:
receive the background sound captured by the user device,
identify a source of the background sound from among a plurality of predetermined sound sources, and
generate a reference background sound based at least in part on the identified source.

2 . The system of claim 1 , wherein the user device is further configured to cancel the background sound in the voice communication based at least in part on the reference background sound.

3 . The system of claim 1 , wherein the server is further configured to cancel the background sound in the voice communication based at least in part on the reference background sound.

4 . The system of claim 1 , further comprising:
another user device configured to participate in the voice communication and cancel the background sound in the voice communication based at least in part on the reference background sound.

5 . The system of claim 1 , wherein the user device is further configured to capture the background sound when a voice call request signal is received as part of an incoming call or when the user device enters a call mode as part of an outgoing call.

6 . The system of claim 1 , wherein the server is further configured to identify the source of the background sound by comparing the background sound to sounds corresponding to the plurality of predetermined sound sources.

7 . The system of claim 6 , wherein the server is further configured to compare the background sound to the sounds corresponding to the plurality of predetermined sound sources by comparing an audio fingerprint of the background sound to audio fingerprints of the sounds corresponding to the plurality of predetermined sound sources.

8 . The system of claim 1 , wherein the server is further configured to generate the reference background sound by adjusting properties of a sound corresponding to the identified source based at least in part on properties of the captured background sound, and wherein the properties of the captured background sound include at least one of a quality of sound and an impulse response.

9 . The system of claim 8 , wherein the properties of the captured background sound are estimated using a channel estimation technique.

10 . The system of claim 1 , wherein the user device is further configured to cancel the background sound based at least in part on the reference background sound using an adaptive noise cancellation technique.

11 . A user device configured to cancel background noise in voice communication, the user device comprising:
a sound detector configured to capture a background sound; a transmitter configured to transmit the captured background sound to a server; a receiver configured to receive, from the server, a reference background sound corresponding to the captured background sound,
wherein the reference background sound is generated based at least in part on a source of the captured background sound, and
wherein the source is identified from among a plurality of predetermined sound sources; and
a noise canceller configured to cancel the background sound in the voice communication based at least in part on the reference background sound.

12 . (canceled)

13 . The user device of claim 11 , wherein the sound detector includes a voice activity detector.

14 . The user device of claim 11 , wherein the captured background sound includes at least one of raw sound data, sound data in a compressed format, and sound features.

15 . (canceled)

16 . (canceled)

17 . (canceled)

18 . A server, comprising:
a receiver configured to receive a background sound from a user device; a sound retrieval unit configured to identify a source of the background sound from among a plurality of predetermined sound sources, wherein the sound retrieval unit is further configured to identify the source of the background sound by comparing the background sound to sounds corresponding to the plurality of predetermined sound sources; a reference sound generation unit configured to generate a reference background sound based at least in part on the identified source; and a transmitter configured to transmit the reference background sound to the user device.

19 . (canceled)

20 . The server device of claim 19 , wherein the sound retrieval unit is further configured to compare the background sound to the sounds corresponding to the plurality of predetermined sound sources by comparing an audio fingerprint of the background sound to audio fingerprints of the sounds corresponding to the plurality of predetermined sound sources.

21 . The server device of claim 18 , wherein the reference sound generation unit is further configured to generate the reference background sound by adjusting properties of a sound corresponding to the identified source based at least in part on properties of the background sound, and wherein the properties of the background sound include at least one of a quality of sound and an impulse response.

22 . The server device of claim 21 , wherein the properties of the background sound are estimated using a channel estimation technique.

23 . The server device of claim 18 , further comprising a noise canceller configured to cancel the background sound in the voice communication based at least in part on the reference background sound.

24 . A method for cancelling background noise in voice communication, the method comprising:
capturing a background sound; identifying a source of the captured background sound from among a plurality of predetermined sound sources; generating a reference background sound based at least in part on the identified sound source; and cancelling the background sound in the voice communication based at least in part on the reference background sound.

25 . The method of claim 24 , wherein the capturing of the background sound includes capturing the background sound when a voice call request signal is received as part of incoming call or when the user device enters a call mode as part of outgoing call.

26 . The method of claim 24 , wherein the identifying of the source of the captured background sound includes comparing the captured background sound to sounds corresponding to the plurality of predetermined sound sources.

27 . The method of claim 26 , wherein the comparing of the captured background sound to the sounds corresponding to the plurality of predetermined sound sources includes comparing an audio fingerprint of the captured background sound to audio fingerprints of the sounds corresponding to the plurality of predetermined sound sources.

28 . The method of claim 24 , wherein the generating of the reference background sound includes generating the reference background sound by adjusting properties of a sound corresponding to the identified source based at least in part on properties of the captured background sound, wherein the properties of the captured background sound include at least one of a quality of sound and an impulse response.

29 . The method of claim 28 , wherein the generating of the reference background sound further includes estimating the properties of the captured background sound using a channel estimation technique.

Assignees

• Empire Technology Dev Llc

Inventors

• Kim Seungil

Classifications

• G10K2210/1081

  Earphones, e.g. for telephones, ear protectors or headsets · CPC title

• G10L21/0216 Primary

  characterised by the method used for estimating noise · CPC title

• G10K2210/3014

  Adaptive noise equalizers [ANE], i.e. where part of the unwanted sound is retained · CPC title

• G10K2210/30231

  Sources, e.g. identifying noisy processes or components · CPC title

• H04M1/19 Primary

  Arrangements of transmitters, receivers, or complete sets to prevent eavesdropping, to attenuate local noise or to prevent undesired transmission; Mouthpieces or receivers specially adapted therefor (circuit arrangements for preventing eavesdropping H04M1/68; telephone cabinets E04H1/14) · CPC title