Apparatus, method, and program for sound quality correction based on identification of a speech signal and a music signal from an input audio signal

• US 7,957,966 B2
• Filed: 02/04/2010
• Issued: 06/07/2011
• Est. Priority Date: 06/30/2009
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Takeuchi, Hirokazu
• Primary Examiner(s): AZAD, ABUL K
• Application Number:
  US12/700,503
• Publication Number:
  US 20100332237A1
• Time in Patent Office: 488 Days
• Field of Search: 704205-219, 846/16, 846/21, 381/56, 381/57, 381/110
• US Class Current: 704/226
• CPC Class Codes: G10H 2210/046 for differentiation between music and non-music signals, based on the identification of musical parameters, e.g. based on tempo detection
• CPC Class Codes: G10H 2210/281 Reverberation or echo
• CPC Class Codes: G10H 2210/295 Spatial effects, musical uses of multiple audio channels, e.g. stereo
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• 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

Abstract

According to one embodiment, a sound quality correction apparatus calculates various feature parameters for identifying the speech signal and the music signal from an input audio signal and, based on the various feature parameters thus calculated, also calculates a speech/music identification score indicating to which of the speech signal and the music signal the input audio signal is close to. Then, based on this speech/music identification score, the correction strength of each of plural sound quality correctors is controlled to execute different types of the sound quality correction processes on the input audio signal.

Claims

1. A sound quality correction apparatus comprising:

a feature parameter calculator configured to calculate various feature parameters to identify a speech signal and a music signal from an input audio signal;

a speech/music identification score calculator configured to calculate a speech/music identification score indicating to which of the speech signal or the music signal the input audio signal is close to, based on the various feature parameters calculated by the feature parameter calculator;

a sound quality corrector configured to execute a plurality of sound quality correction processes of different types on the input audio signal; and

a controller configured to control a correction strength for each of the sound quality correction processes executed by the sound quality corrector, based on the speech/music identification score calculated by the speech/music identification score calculator, the controller being configured to determine a target correction strength for each of the sound quality correction processes executed by the sound quality corrector based on the speech/music identification score, and to change a present correction strength stepwise toward the target correction strength for each of the sound quality correction processes executed by the sound quality corrector, based on a forward transition time and a backward transition time which are predetermined for each of the sound quality correction processes executed by the sound quality corrector.

2. The sound quality correction apparatus of claim 1,

wherein the controller is configured to control the correction strength for each of the sound quality correction processes of different types executed by the sound quality corrector, based on the speech/music identification score at preset intervals.

3. The sound quality correction apparatus of claim 1,

wherein the feature parameter calculator is configured to calculate various feature parameters to identify the music signal and the background sound signal from the input audio signal,

the apparatus comprising:

a music/background sound identification score calculator configured to calculate a music/background sound identification score indicating to which of the music signal or the background sound signal the input audio signal is close to, based on the various feature parameters to identify the music signal and the background sound signal calculated by the feature parameter calculator; and

a speech/music identification score corrector configured in such a manner that in the case where the speech/music identification score calculated by the speech/music identification score calculator indicates a music signal and the music/background sound identification score calculated by the music/background sound identification calculator indicates a background sound signal, then the speech/music identification score is corrected based on the value of the music/background sound identification score,

wherein the controller is configured to control the correction strength for each of the sound quality correction processes executed by the sound quality corrector, based on the speech/music identification score corrected by the speech/music identification score corrector.

4. The sound quality correction apparatus of claim 1,

wherein the controller includes a table describing correlations between the speech/music identification score and the correction strength determined for each of the sound quality correction processes executed by the sound quality corrector, and in the case where the speech/music identification score is input, the table is referred to and the correction strength for each of the sound quality correction processes executed by the sound quality corrector is determined.

5. The sound quality correction apparatus of claim 1,

wherein the sound quality corrector is configured to execute at least one of the reverberation process, the wide stereo process, the center emphasis process, the equalization process and the surround process on the input audio signal.

6. A sound quality correction method comprising:

calculating various feature parameters to identify a speech signal and a music signal from an input audio signal;

calculating a speech/music identification score indicating to which of the speech signal or the music signal the input audio signal is close to, based on the calculated various feature parameters;

executing a plurality of sound quality correction processes of different types on the input audio signal;

controlling a correction strength for each of the sound quality correction processes executed by a sound quality corrector, based on the calculated speech/music identification score, the controlling comprising determining a target correction strength for each of the sound quality correction processes executed by the sound quality corrector based on the speech/music identification score, and changing a present correction strength stepwise toward the target correction strength for each of the sound quality correction processes executed by the sound quality corrector, based on a forward transition time and a backward transition time which are predetermined for each of the sound quality correction processes executed by the sound quality corrector.

7. A non-transitory computer readable medium having stored thereon a sound quality correction program which is executable by a computer, the sound quality correction program controlling the computer to execute the functions of:

calculating various feature parameters to identify a speech signal and a music signal from an input audio signal;

calculating a speech/music identification score indicating to which of the speech signal or the music signal the input audio signal is close to, based on the various feature parameters calculated; and

controlling a correction strength for each of the sound quality correction processes executed by a sound quality corrector, based on the calculated speech/music identification score, the controlling comprising determining a target correction strength for each of the sound quality correction processes executed by the sound quality corrector based on the speech/music identification score, and changing a present correction strength stepwise toward the target correction strength for each of the sound quality correction processes executed by the sound quality corrector, based on a forward transition time and a backward transition time which are predetermined for each of the sound quality correction processes executed by the sound quality corrector.