JPH04359298A - Music voice discriminating device - Google Patents

Abstract

PURPOSE:To provide a music voice discriminating device which discriminates stereophonic music from announcing voice in the news in an FM broadcasting program and provides a sound field control which is suitable to the source. CONSTITUTION:Stereophonic sound signals, which are inputted from an Lch input terminal 1 and an Rch input terminal 2, are added and subtracted at an adder section 3 and a subtractor section 4, respectively and are inputted to a discriminating section 5 as sum and difference signals. At the discriminating section 5, a sound presence and absence judging section 6, which configures the discriminating section, decides a sound condition or a no sound condition by the sum signal level. If a presence of sound is detected, a music voice judging section 7 judges the sound as a music or a voice employing the amplitude ratio of the difference and sum signals. If no judgement is conducted due to a lack of precision, a decision is withheld. The no sound, music, voice or withholding of a discrimination judgements are transferred to a signal processing section 8 as control signals.

Description

[Detailed description of the invention]

0001

[Industrial Application Field] The present invention can be applied to sound field control-related equipment that can achieve a good sense of spaciousness, localization, and clarity according to the type of source being played in a listening room or vehicle interior. The present invention relates to a possible music voice discrimination device.

0002

[Background Art] In recent years, technological trends in the audio field have been changing from original sound reproduction to original sound field reproduction. Sound field control devices are being developed that create a sound field similar to a concert hall by adding sound effects and playing them through multi-channel speakers. Some devices have been devised that have a source discrimination function that can automatically adjust the
Publication No.).

[0003] As an example of the conventional source discrimination function described above, the magnitude of the difference signal amplitude between the L and R 2ch signals transmitted in stereo is calculated, and the level of the sound effect is set so as to be inversely proportional to the magnitude of the difference signal amplitude. That is, when playing back music, if the source has few reverberation components, the difference signal amplitude will be small, so more sound effects will be added, and in the opposite case, less sound effects will be added.

0004

[Problem to be Solved by the Invention] However, with the above configuration, for example, when receiving an FM broadcast, if the stereo music broadcast changes to monaural sound such as news, the L
, the difference signal of the R signal is almost zero, and it is judged as dry music with extremely few reverberation components, so the added sound effect is at the maximum level, resulting in a problem of decreased clarity. .

[0005] Furthermore, when playing stereo music, the amplitude values of the L and R difference signals constantly vary depending on the silence between songs, each part in the song, the input signal level, etc. There was a problem in that the sound effect level fluctuated wildly, making it unnatural.

The present invention solves the above-mentioned problems and provides a music/sound discriminating device that can determine with high accuracy whether the source is music or voice, including determining whether the source is a sound state or a soundless state, especially when listening to FM broadcasts. The purpose is to provide.

[0007]

[Means for Solving the Problems] In order to achieve the above object, the music sound discriminating device of the present invention includes an adding section for adding input L and R signals, a subtracting section for subtracting input signals, and a discriminating section. The determination unit includes a sound/non-sound determination unit that determines whether the input L and R signals have sound or no sound, a music comparison unit that determines whether or not the input signal is music if there is sound, and a sound and a music sound judgment section, which is composed of a sound comparison section that judges whether or not the music sound is the same.

[0008]

[Operation] With the above configuration, the present invention first determines that there is no sound when the amplitude value of the L and R summed signals is less than a preset certain value in the utterance/non-sound determination section, and does not determine whether it is a musical sound. . In the case of sound, the music comparison section and the audio comparison section that constitute the music sound judgment section determine if the amplitude ratio of the L, R difference signal and the sum signal is equal to or higher than a preset certain value for music judgment. is determined to be music, if it is less than a certain value for voice determination, it is determined to be voice, and if neither of the above is true, determination of music voice is reserved.

[0009] Therefore, when processing an input signal such as adding sound effects, it is possible to avoid unnecessary changes in processing contents when there is no sound. When there is sound, the appropriate signal processing content can be changed only if it can be definitely determined that it is music or voice, and if it cannot be determined whether it is music or voice, the current processing content is maintained, etc., so that the wrong direction is detected. It is possible to avoid changing the processing content.

[0010] Therefore, it is possible to eliminate uncertain factors caused by fluctuations in L and R signal components, changes in volume, disturbance noise, etc. due to parts of the voice or music, and it is possible to reliably determine the musical voice. Using the results, stable acoustic signal processing becomes possible.

[0011]

DESCRIPTION OF THE PREFERRED EMBODIMENTS A music voice discrimination device according to an embodiment of the present invention will be described below with reference to the drawings.

(FIG. 1) is a block diagram showing an example of the configuration of the music voice discrimination device of the present invention, and (FIG. 2) shows a discrimination algorithm in a discrimination section which is a component of the music voice discrimination device of the present invention. It is a flowchart.

[0013] In (Fig. 1), 1 and 2 are respectively FM
Lch signal input terminal and Rch signal input terminal that receive stereo signals transmitted from a signal source such as a tuner; 3 is an addition unit that adds the input L and R signals; 4 is L and R
A subtraction unit that subtracts the signal, 6 is L and R from the addition unit 3.
A sound/non-sound determining section 7 determines whether the input signal is sound or no sound based on the sum signal; 5 is a discrimination unit composed of a voice/non-sound discrimination unit 6 and a music/speech discrimination unit 7; 8 is a discrimination unit that determines whether music or voice is music or voice based on the control signal transferred from the discrimination unit 5; This is a signal processing unit that performs acoustic signal processing suitable for.

In FIG. 2, reference numeral 9 denotes a music comparison section that determines whether the input signal is music based on a comparison between the amplitude ratio of the L and R difference signals and the sum signal and a set constant value; and 10, a music comparison section; This is an audio comparison section that determines whether the input signal is audio based on a comparison between the amplitude ratio and a set constant value, and these constitute the music audio determination section 7.

The operation of the music voice discriminating device according to an embodiment of the present invention constructed as described above will be explained below.

In (FIG. 1), the acoustic signals input from the Lch input terminal 1 and the Rch input terminal 2 are input to the adder 3.
and the subtracter 4 add and subtract, respectively, and send the results to the discriminator 5. The discrimination unit 5 determines whether the input acoustic signal is silent or has sound, and if it has sound, whether it is music or voice, and sends the determination result to the signal processing unit 8 as a control signal, according to the procedure described in detail below. Forward. In the signal processing section 8, L
L input to channel input terminal 1 and Rch input terminal 2,
Upon receiving the R signal, based on the control signal, if it is determined to be music, signal processing suitable for music is performed, and if it is determined to be voice, signal processing suitable for voice is performed. In addition, when it is determined that there is no sound, or when it is not possible to reliably distinguish the music sound even when there is sound, the current signal processing is maintained to avoid the risk of changing the processing content in the wrong direction.

Next, the discrimination procedure in the discrimination section 5 will be explained in detail based on (FIG. 2). In the determination, first, in the utterance/non-speech determining section 6 constituting the determining section 5, the amplitude value of the L, R sum signal is compared with a preset constant value 2-k. The value of the constant k is set so that the above-mentioned constant value is, for example, slightly larger than the noise level when the signal is silent. Therefore, as a result of comparison, if the sum signal is larger, it is determined that there is sound. , the process moves on to the next determination by the music comparison section 9. In the opposite case, it is determined that there is no sound, and a control signal indicating the silence is sent to the signal processing section 8 without determining the musical sound.

If it is determined that there is a sound in the above, then the music comparison section 9 constituting the music sound judgment section 7 performs L,
The amplitude value of the R difference signal is compared with the result of multiplying the amplitude value of the L, R sum signal by a preset constant value 2-m. If the difference signal is larger, it is determined to be music,
A control signal indicating that it is music is sent to the signal processing section 8. In the opposite case, the process moves to the next determination by the voice comparison unit 10.

This comparison operation determines whether the difference component of the stereo audio signal is equal to or greater than a certain percentage of the sum component. Generally, in the case of stereo music, L,
The difference component of the R signal becomes significantly larger. Therefore, by setting the constant m so that the above constant value 2-m is sufficiently larger than the upper limit of the ratio of the difference component to the sum component in the case of an announcement voice, taking into account the noise level, the input signal can be In the case of audio, erroneous determination can be reliably avoided, and in the case of music, it can be determined as music with a high probability.

[0020] If it is not determined as music in the above,
Next, in the audio comparison section 9, the amplitude value of the L, R difference signal is also compared with the result of multiplying the amplitude value of the L, R sum signal by a preset constant value 2-n. If the difference signal is smaller, it is determined that it is voice, and a control signal indicating that it is voice is sent to the signal processing section 8. In the opposite case, since it indicates that neither music nor voice can be reliably determined, a control signal indicating reservation of determination is sent to the signal processing unit 8, or the control signal is not transferred.

This comparison operation determines whether the difference component of the stereo sound signal is less than a certain percentage of the sum component. As mentioned above, in the case of an announcement voice, the difference component between the L and R signals is generally much smaller than in the case of stereo music. Therefore, the above constant value 2-
By setting the constant n so that n is close to the upper limit of the ratio of the difference component to the sum component in the case of announcement voice, taking into account the noise level, when the input signal is voice, it is possible to detect voice with a high probability. It can be determined that Furthermore, even when the music comparing section 9 does not determine that the music is music, it is possible to avoid, with a high probability, repeating the erroneous determination that the music is audio.

[0022] Note that since the music comparison section 9 and the audio comparison section 10 use the amplitude ratio of the L, R difference signal and the sum signal, the volume level of the input audio signal may change. However, it is possible to continue extremely stable determination operations.

[0023]

[Effects of the Invention] As described above, the music audio discrimination device of the present invention uses the sum signal of the input stereo sound signals to
First, it is determined whether there is sound or no sound, and if there is sound, it is further determined whether it is music or voice based on the magnitude relationship between the amplitude ratio of the difference signal and the sum signal and a preset constant value. Since the judgment is withheld when it is difficult to distinguish between music and voice that occur stochastically, it is possible to avoid changing the signal processing in the wrong direction by forcing a judgment.
Stable discrimination can be performed without being affected by changes in the volume of the acoustic signal or noise level.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an example of the configuration of a music voice discrimination device according to the present invention.

FIG. 2 is a flowchart showing a discrimination algorithm in a discrimination section which is a component of the music voice discrimination device of the present invention.

[Explanation of symbols]

1 Lch input terminal 2 Rch input terminal 3 Addition section 4 Subtraction section 5 Discrimination section 6 Speech/silence judgment unit 7 Music audio judgment section 8 Signal processing section 9 Music comparison section 10 Audio comparison section

Claims (4)

[Claims] 1. An addition unit that adds input L and R signals of 2 channels, a subtraction unit that calculates a difference signal between the L and R signals, and whether the L and R signals are in a silent state or a sound state, and a determining unit that determines whether it is in a music playback state or an audio playback state when there is sound, and the determining unit is based on the amplitude of the L signal and the R signal or the amplitude of the output signal of the adding unit. A utterance/non-speech determination section that determines whether there is a sound or not, and whether the input L and R signals are music or voice based on the amplitude of the output signal of the addition section and the amplitude of the output signal of the subtraction section. 1. A music sound discriminating device comprising: a music sound determining section that performs judgment. 2. The utterance/non-utterance determination unit includes a utterance/non-utterance comparison unit that compares the amplitude of the L signal and the R signal or the amplitude of the output signal of the adding unit with a preset utterance/non-utterance determination coefficient. 2. The music sound discriminating device according to claim 1, wherein if the amplitude is less than the utterance/non-utterance determination coefficient, it is determined that there is no sound, and if it is greater than that, it is determined that there is a sound. 3. The music sound determination section includes a music comparison section that compares the amplitude of the output signal of the addition section and a preset music determination coefficient with the amplitude of the output signal of the subtraction section; an audio comparison section that compares the amplitude of the output signal of the subtraction section with the amplitude of the output signal of the subtraction section and the result of multiplying the amplitude of the output signal of the subtraction section by a preset audio determination coefficient; 2. The music reproduction state is determined when the amplitude of the output signal is larger, and the audio comparison section determines the audio reproduction state when the amplitude of the output signal of the subtraction section is smaller. music voice discrimination device. 4. Any one of claims 1 to 3, characterized in that when the utterance/non-sound determination unit determines that there is no sound, the music/voice determination unit does not perform the determination or ignores the determination result. A music voice discriminating device described in Crab.