Systems, non-transitory computer-readable media and methods for voice quality enhancement

1. A method performed by a server for controlling an audio characteristic of an electronic device, the method comprising:

receiving, from a first electronic device of a plurality of electronic devices, first audio characteristic information measured during a first call of the first electronic device, the first audio characteristic information being measured under control of a first application executed on the first electronic device;

receiving, from the first electronic device, first device characteristic information of the first electronic device, the first device characteristic information being collected under control of the first application;

first classifying the first audio characteristic information based on the first device characteristic information;

generating environment setting information corresponding to device characteristic information of each of the plurality of electronic devices based on classified audio characteristic information, the environment setting information including first environment setting information corresponding to the first device characteristic information based on the first classifying;

receiving, from a second electronic device among the plurality of electronic devices, second device characteristic information of the second electronic device, the second device characteristic information being collected under control of a second application executed on the second electronic device; and

sending second environment setting information corresponding to the second device characteristic information to the second electronic device, the second environment setting information being applied under control of the second application to control an audio characteristic for a second call of the second electronic device.

2. The method of claim 1 , further comprising:

receiving, from the second electronic device, second audio characteristic information measured during the second call, the second audio characteristic information being measured under control of the second application; and

second classifying the second audio characteristic information based on the second device characteristic information.

3. The method of claim 2 , wherein the receiving the second audio characteristic information is performed after the sending the second environment setting information.

4. The method of claim 1 , wherein the first audio characteristic information includes at least one of an echo return loss (ERL), a residual echo level (L RES ), an echo return loss enhancement (ERLE), a noise level, or an average voice level.

5. The method of claim 1 , wherein the device characteristic information includes

first information associated with at least one of

information used to specify a type or an operating system of an electronic device of the plurality of electronic devices,

a specification associated with a performance of the electronic device, or

a specification associated with an audio characteristic of the electronic device, and

second information associated with at least one of a call area or a call mode of the electronic device.

6. The method of claim 5 , wherein the specification associated with the performance of the electronic device includes information associated with at least one of a central processing unit (CPU) included in the electronic device or a memory included in the electronic device.

7. The method of claim 5 , wherein the specification associated with the audio characteristic of the electronic device includes information associated with at least one of a system delay of the electronic device, an audio clipping of the electronic device, power noise of the electronic device, a clock of a microphone included in the electronic device, a clock of a speaker included in the electronic device, or whether a voice quality enhancement (VQE) system is supported in the electronic device.

8. The method of claim 1 , wherein

the first classifying includes statistically classifying the first audio characteristic information based on the first device characteristic information, and

the first environment setting information includes an environment setting value of the first electronic device that is set based on the statistically classified first audio characteristic information according to the first device characteristic information.

9. The method of claim 8 , wherein the environment setting value includes a setting value of at least one of a system delay, an acoustic echo cancellation (AEC), a noise suppression (NS), a high power field (HPF), an automatic gain control (AGC), a skew compensation, a VQE system, or a codec of the first electronic device.

10. The method of claim 1 , further comprising:

determining the second environment setting information by searching the generated environment setting information using the second device characteristic information, the second environment setting information being the same as the first environment setting information when the second device characteristic information is the same as the first device characteristic information.

11. A method performed by an electronic device of a plurality of electronic devices to control an audio characteristic of the electronic device, the method comprising:

collecting first device characteristic information under control of an executed application;

sending the first device characteristic information to a server under control of the executed application;

receiving first environment setting information provided by the server during a call, the receiving being performed under control of the executed application, the first environment setting information being based on the first device characteristic information;

applying the first environment setting information to control the audio characteristic for voice quality enhancement of the call;

collecting first audio characteristic information by analyzing voice data input during the call; and

sending the first audio characteristic information to the server,

wherein, at the server, audio characteristic information, including the first audio characteristic information, transmitted from the plurality of electronic devices is classified based on corresponding device characteristic information transmitted from the plurality of electronic devices, and environment setting information corresponding to respective device characteristic information is generated based on the classified audio characteristic information corresponding to respective device characteristic information, the environment setting information including the first environment setting information corresponding to the first device characteristic information.

12. The method of claim 11 , wherein the audio characteristic information includes at least one of an echo return loss (ERL), a residual echo level (L RES ), an echo return loss enhancement (ERLE), a noise level, or an average voice level.

13. The method of claim 11 , wherein the first device characteristic information includes

first information associated with at least one of

information used to specify a type or an operating system of the electronic device,

a specification associated with a performance of the electronic device, or

a specification associated with an audio characteristic of the electronic device, and

second information associated with at least one of a call area or a call mode of the electronic device.

14. The method of claim 11 , wherein

the audio characteristic information is statistically classified based on the corresponding device characteristic information, and

the environment setting information includes an environment setting value that is set based on the statistically classified audio characteristic information according to the corresponding device characteristic information.

15. The method of claim 14 , wherein the environment setting value includes a setting value of at least one of a system delay, an acoustic echo cancellation (AEC), a noise suppression (NS), a high power field (HPF), an automatic gain control (AGC), a skew compensation, a VQE system, or a codec of the electronic device.

16. A non-transitory computer-readable medium storing program code including instructions that, when executed by one or more processors, causes the one or more processors to:

receive, from a first electronic device of a plurality of electronic devices, first audio characteristic information measured during a first call of the first electronic device, the first audio characteristic information being measured under control of a first application executed on the first electronic device;

receive, from the first electronic device, first device characteristic information of the first electronic device, the first device characteristic information being collected under control of the first application;

first classify the first audio characteristic information based on the first device characteristic information;

generate environment setting information corresponding to device characteristic information of each of the plurality of electronic devices based on classified audio characteristic information, the environment setting information including first environment setting information corresponding to the first device characteristic information based on the first classification;

receive, from a second electronic device among the plurality of electronic devices, second device characteristic information of the second electronic device, the second device characteristic information being collected under control of a second application executed on the second electronic device; and

send second environment setting information corresponding to the second device characteristic information to the second electronic device, the second environment setting information being applied under control of the second application to control an audio characteristic for a second call of the second electronic device.

17. The non-transitory computer-readable medium of claim 16 , wherein the first audio characteristic information includes at least one of an echo return loss (ERL), a residual echo level (L RES ), an echo return loss enhancement (ERLE), a noise level, or an average voice level.

18. The non-transitory computer-readable medium of claim 16 , wherein the device characteristic information includes

information associated with at least one of

information used to specify a type or an operating system of an electronic device of the plurality of electronic devices,

a specification associated with a performance of the electronic device, or

a specification associated with an audio characteristic of the electronic device, and

information associated with at least one of a call area or a call mode of the electronic device.

19. The non-transitory computer-readable medium of claim 16 , wherein

the first classification includes statistically classifying the first audio characteristic information based on the first device characteristic information, and

the environment setting information includes an environment setting value of the first electronic device that is set based on the statistically classified first audio characteristic information according to the first device characteristic information.