SOUND QUALITY CORRECTION APPARATUS, SOUND QUALITY CORRECTION METHOD AND PROGRAM FOR SOUND QUALITY CORRECTION

• US 20100158261A1
• Filed: 10/09/2009
• Published: 06/24/2010
• Est. Priority Date: 12/24/2008
• Status: Active Grant

• Current Assignee: Kioxia Corporation
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yonekubo, Hiroshi, Takeuchi, Hirokazu
• Granted Patent: US 7,864,967 B2
• Time in Patent Office: Days
• US Class Current: 381/56
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 21/0264 characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04S 7/30 Control circuits for electronic adaptation of the sound field

Abstract

According to one embodiment, various feature parameters are calculated for distinguishing between a speech and music and between music and background sound for an input audio signal. With the feature parameters, score determination is made as to whether the input audio signal is close to a speech signal or a music signal. If the input audio signal is determined to be close to music, the preceding score determination result is corrected considering the influence of background sound. Based on the corrected score value, a sound quality correction process for a speech or music is applied to the input audio signal.

Claims

1. A sound quality correction apparatus comprising:

a feature parameter calculator configured to calculate various feature parameters for distinguishing between a speech signal and a music signal and distinguishing between the music signal and a background sound signal, for an input audio signal;

a speech and music discrimination score calculator configured to calculate a speech and music discrimination score indicating which of the speech signal and the music signal the input audio signal is close to, based on the various feature parameters for distinguishing between the speech signal and the music signal calculated in the feature parameter calculator;

a music and background sound discrimination score calculator configured to calculate a music and background sound discrimination score indicating which of the music signal and the background sound signal the input audio signal is close to, based on the various feature parameters for distinguishing between the music signal and the background sound signal calculated in the feature parameter calculator;

a speech and music discrimination score corrector configured to correct the speech and music discrimination score based on a value of the music and background sound discrimination score when the speech and music discrimination score calculated in the speech and music discrimination score calculator indicates the music signal and when the music and background sound discrimination score calculated in the music and background sound discrimination score calculator indicates the background sound signal; and

a sound quality corrector configured to determine closeness to the speech signal or the music signal of the input audio signal based on the speech and music discrimination score corrected in the speech and music discrimination score corrector and perform a sound quality correction process for the speech or the music.

2. The sound quality correction apparatus of claim 1, wherein

the speech and music discrimination score corrector is configured to multiply the music and background sound discrimination score calculated in the music and background sound discrimination score calculator by a predetermined factor and add the music and background sound discrimination score multiplied by the factor to the speech and music discrimination score calculated in the speech and music discrimination score calculator to thereby correct the speech and music discrimination score.

3. The sound quality correction apparatus of claim 1, wherein

the speech and music discrimination score calculator is configured to multiply each of various feature parameters for distinguishing between the speech signal and the music signal calculated in the feature parameter calculator by a weighting factor, the weighting factor being calculated by learning each feature parameter by using a speech signal and a music signal prepared in advance as reference data, and calculate a total sum of each feature parameter multiplied by the weighting factor as the speech and music discrimination score, and

the music and background sound discrimination score calculator is configured to multiply each of various feature parameters for distinguishing between the music signal and the background sound signal calculated in the feature parameter calculator by a weighting factor, the weighting factor bring calculated by learning each feature parameter by using a music signal and a background sound signal prepared in advance as reference data, and calculate a total sum of each feature parameter multiplied by the weighting factor as the music and background sound discrimination score.

4. The sound quality correction apparatus of claim 1, wherein

the speech and music discrimination score calculator is configured to divide the input audio signal by a predetermined unit and calculate a speech and music discrimination score by the unit after dividing.

5. The sound quality correction apparatus of claim 4, further comprising

a stabilizing parameter adder configured to add a stabilizing parameter to the speech and music discrimination score for the sound quality corrector to increase a correction intensity for music, when the speech and music discrimination score calculated by the predetermined unit of the input audio signal in the speech and music discrimination score calculator indicates a music signal a predetermined number of times or more continuously, and

to add a stabilizing parameter to the speech and music discrimination score for the sound quality corrector to reduce correction for music, when the speech and music discrimination score calculated by the predetermined unit of the input audio signal in the speech and music discrimination score calculator indicates a speech signal a predetermined number of times or more continuously.

6. The sound quality correction apparatus of claim 1, further comprising

a level corrector configured to apply a level correction process to the audio signal to which a sound quality correction process is applied by the sound quality corrector so that a level variation with the input audio signal is settled within a predetermined range.

7. A sound quality correction method comprising:

calculating various feature parameters for distinguishing between a speech signal and a music signal and distinguishing between the music signal and a background sound signal, for an input audio signal;

calculating a speech and music discrimination score indicating which of the speech signal and the music signal the input audio signal is close to, based on the various feature parameters for distinguishing between the speech signal and the music signal;

calculating a music and background sound discrimination score indicating which of the music signal and the background sound signal the input audio signal is close to, based on the various feature parameters for distinguishing between the music signal and the background sound signal;

correcting the speech and music discrimination score based on a value of the music and background sound discrimination score when the speech and music discrimination score indicates the music signal and when the music and background sound discrimination score indicates the background sound signal; and

determining closeness to the speech signal or the music signal of the input audio signal based on the corrected speech and music discrimination score and performs a sound quality correction process for a speech or music.

8. A program for sound quality correction to cause a computer to execute:

a process of calculating various feature parameters for distinguishing between a speech signal and a music signal and distinguishing between the music signal and a background sound signal, for an input audio signal;

a process of calculating a speech and music discrimination score indicating which of the speech signal and the music signal the input audio signal is close to, based on the various feature parameters for distinguishing between the speech signal and the music signal;

a process of calculating a music and background sound discrimination score indicating which of the music signal and the background sound signal the input audio signal is close to, based on the various feature parameters for distinguishing between the music signal and the background sound signal;

a process of correcting the speech and music discrimination score based on a value of the music and background sound discrimination score when the speech and music discrimination score indicates the music signal and when the music and background sound discrimination score indicates the background sound signal; and

a process of determining closeness to the speech signal or the music signal of the input audio signal based on the corrected speech and music discrimination score and performing a sound quality correction process for a speech or music.