Method and apparatus for improving call quality in noise environment

1. A voice signal processing method comprising:

acquiring a real-time near-end noise signal;

acquiring a far-end voice signal according to an incoming call;

measuring subjective speech quality and perceptual-objective speech quality of test signals generated based on a reference signal and the real-time near-end noise signal;

selecting at least one speech quality enhancement method based on the subjective speech quality and the perceptual-objective speech quality; and determining parameters that are to be applied to the selected at least one speech quality enhancement method; and

enhancing speech quality of the far-end voice signal by using the selected at least one speech quality enhancement method, based on the determined parameters,

wherein the test signals are generated by mixing the acquired real-time near-end noise signal with the reference signal whose speech quality is enhanced by applying a combination of parameter values to speech quality enhancement methods.

2. The voice signal processing method of claim 1 , wherein determining of the parameters comprises:

measuring speech quality of the test signals based on the subjective speech quality and the perceptual-objective speech quality; and

determining a combination of parameter values when the measured speech quality of the test signals is optimal, as the parameters.

3. The voice signal processing method of claim 2 , wherein the determining of the parameters further comprises

determining a weight for the subjective speech quality and a weight for the perceptual-objective speech quality based on context information for the incoming call,

wherein the speech quality of the test signals is measured by applying the weight for the subjective speech quality to the subjective speech quality and applying the weight for the perceptual-objective speech quality to objective speech quality.

4. The voice signal processing method of claim 1 , wherein the subjective speech quality is measured based on subjective speech quality prediction values corresponding to the parameter values.

5. The voice signal processing method of claim 1 , further comprising:

monitoring the real-time near-end noise signal; and

updating the parameters when a result of monitoring the real-time near-end noise signal indicates that characteristics of the real-time near-end noise signal change.

6. A voice signal processing method comprising:

acquiring a real-time near-end noise signal;

acquiring a far-end voice signal according to an incoming call;

transmitting information about the acquired real-time near-end noise signal;

receiving information about at least one speech quality enhancement method selected based on subjective speech quality and perceptual-objective speech quality of test signals generated based on a reference signal and the real-time near-end noise signal, and information about optimal values of parameters that are to be applied to the selected at least one speech quality enhancement method; and

enhancing speech quality of the far-end voice signal by using the selected at least one speech quality enhancement method; based on the received optimal values of the parameters,

wherein the test signals are generated by mixing the acquired real-time near-end noise signal with the reference signal whose speech quality is enhanced by applying a combination of parameter values to speech quality enhancement methods.

7. The voice signal processing method of claim 6 , wherein the far-end voice signal is a voice signal whose speech quality is enhanced by applying optimal values of parameters determined based on a reference signal and a real-time far-end noise signal to at least one speech quality enhancement method.

8. A voice signal processing apparatus comprising:

an inputter configured to acquire a real-time near-end noise signal;

a receiver configured to acquire a far-end voice signal according to an incoming call; and

a speech quality enhancer configured to measure subjective speech quality and perceptual-objective speech quality of test signals generated based on a reference signal and the real-time near-end noise signal, to select at least one speech quality enhancement method based on the subjective speech quality and the perceptual-objective speech quality, to determine parameters that are to be applied to the selected at least one speech quality enhancement method, and to enhance speech quality of the far-end voice signal by using the selected at least one speech quality enhancement method, based on the determined parameters,

wherein the test signals are generated by mixing the acquired real-time near-end noise signal with the reference signal whose speech quality is enhanced by applying a combination of parameter values to speech quality enhancement methods.

9. The voice signal processing apparatus of claim 8 , wherein the speech quality enhancer measures speech quality of the test signals based on the subjective speech quality and the perceptual-objective speech quality, and determines a combination of parameter values when the measured speech quality of the test signals is optimal, as the parameters.

10. The voice signal processing apparatus of claim 9 , wherein the speech quality enhancer measures the speech quality of the test signals by determining a weight for the subjective speech quality and a weight for the perceptual-objective speech quality based on context information for the incoming call, applying the weight for the subjective speech quality to the subjective speech quality and applying the weight for the perceptual-objective speech quality to objective speech quality.

11. The voice signal processing apparatus of claim 8 , wherein the subjective speech quality is measured based on subjective speech quality prediction values corresponding to the parameter values.

12. The voice signal processing apparatus of claim 8 , wherein the speech quality enhancer monitors the real-time near-end noise signal, and updates the parameters when a result of monitoring the real-time near-end noise signal indicates that characteristics of the real-time near-end noise signal change.

13. A non-transitory computer-readable recording medium having recorded thereon a program that when executed by a processor, causes the processor to:

acquire a real-time near-end noise signal;

acquire a far-end voice signal according to an incoming call;

measure subjective speech quality and perceptual-objective speech quality of test signals generated based on a reference signal and the real-time near-end noise signal;

select at least one speech quality enhancement method based on the subjective speech quality and the perceptual-objective speech quality;

determine parameters that are to be applied to the selected at least one speech quality enhancement method; and

enhance speech quality of the far-end voice signal by using the selected at least one speech quality enhancement method, based on the determined parameters,

wherein the test signals are generated by mixing the acquired real-time near-end noise signal with the reference signal whose speech quality is enhanced by applying a combination of parameter values to speech quality enhancement methods.