JP2008268369A - Vibrato detecting device, vibrato evaluating device, vibrato detecting method, and vibrato evaluating method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detects a section in which a vibrato technique is used and further to evaluate skill in vibrato technique in the section. <P>SOLUTION: A control unit 11 detects pitches for each frame of a predetermined time length from singer voice data, generates pitch data representing the detected pitches, and performs filter processing for extracting a specified frequency component. Then the control unit 11 computes pitches of the pitch data subjected to the filter processing for each note of melody pitch data based upon a pitch of the melody pitch data as a zero reference value, and extracts various parameters from temporal variation in pitch. Further, the control unit 11 specifies a section to be sung with the vibrato technique according to the extracted parameters and evaluates skill in vibrato technique of the singer voice data in the section using the various parameters extracted from the singer voice data. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a technique for identifying a place where a vibrato technique is used from sound data, and a technique for evaluating the skill of the vibrato technique in sound data.

In the karaoke apparatus, an apparatus for scoring a singer's skill of singing or displaying a message indicating the singing instruction content to perform singing instruction has been proposed. In such a karaoke apparatus, for example, when scoring and teaching about the vibrato technique, first, a section where the vibrato technique is used (hereinafter referred to as a vibrato section) is identified from a singing voice as a model, A method of teaching can be considered. Note that the vibrato technique is a singing technique that gives the sound a rich reverberation by producing a timbre that slightly raises and lowers the pitch while stretching the sound.
As a method for specifying a vibrato section, for example, Patent Document 1 proposes a method for specifying a section in which the pitch of input data vibrates as a vibrato section.
JP 2006-195449 A

Now, according to the technique described in Patent Document 1, when trying to specify a vibrato section using the vibration of the pitch as an index, a section including a technique different from vibrato such as tremolo is specified as a vibrato section. There was a problem. In tremolo, the pitch variation pattern is generally larger than that of vibrato, and the pitch fluctuation pattern is generally unstable.
Moreover, although the said patent document 1 is disclosed about the technique which specifies a vibrato area, the technique which evaluates the skill of the vibrato technique in the specified area is not disclosed.

  The present invention has been made under the background described above, and provides a technique for detecting a section in which the vibrato technique is used from sound data and further evaluating the skill of the vibrato technique in the detected section. With the goal.

  A vibrato detecting device according to a preferred aspect of the present invention includes a storage unit that stores melody pitch data representing a pitch of a melody, pitch data representing a detected pitch by detecting the pitch in units of frames of a predetermined time length from sound data. The pitch detection means for generating the filter, the filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means, and the melody pitch data stored in the storage means Using the pitch as a zero reference value, a pitch difference data value representing a relative value between the pitch data filtered by the filter processing means and the zero reference value is calculated, and the pitch difference data is changed from negative to positive. Or a zero-cross point specifying means for specifying a point that changes from positive to negative as a zero-cross point; In the pitch difference data, the time at which the pitch value becomes the maximum and the minimum is specified in the pitch difference data, and the adjacent maximum is specified. A pitch vibration width data generating means for generating pitch vibration width data from the difference between the value and the minimum value, and the pitch vibration width data in a predetermined mode in the section specified by the specifying means Output means for outputting information indicating the section specified by the specifying means.

  In the vibrato detection device according to a preferred aspect of the present invention, the specifying unit measures a time interval at which the zero cross point specified by the zero cross point specifying unit appears, and the measured time interval is within a predetermined range. There may also be specified a section in which the state is continuously detected a predetermined number of times or more.

  In the vibrato detection device according to a preferred aspect of the present invention, the output means calculates a straight line that approximates a time change of the pitch fluctuation width data in the section specified by the specifying means, and the inclination of the calculated straight line When the absolute value of is smaller than a predetermined threshold, information indicating the section specified by the specifying means may be output.

  In the vibrato detecting device according to a preferred aspect of the present invention, the output means calculates a time average of the pitch fluctuation data in the section specified by the specifying means, and the calculated time average falls within a predetermined range. In some cases, information indicating the section specified by the specifying unit may be output.

  A vibrato evaluation device according to a preferred embodiment of the present invention includes a storage unit that stores melody pitch data that represents a pitch of a melody, pitch data that detects the pitch in units of frames of a predetermined time length from sound data, and represents the detected pitch data A pitch detection means for generating a filter processing means for extracting a specific frequency component from the pitch data generated by the pitch detection means, a receiving means for receiving data indicating a vibrato section, and In the vibrato section indicated by the data received by the receiving means, the pitch represented by the melody pitch data stored in the storage means is set as a zero reference value, and the pitch data filtered by the filter processing means and the zero reference value Calculating the pitch value of the pitch difference data representing the relative value of the pitch Pitch vibration width data generating means for specifying the time when the minute data becomes maximum and minimum, and generating pitch vibration width data from the difference between the adjacent maximum and minimum values, and the data received by the receiving means In the vibrato section shown, when the pitch vibration width data is in a predetermined form, an output means for calculating a high evaluation and outputting the evaluation is provided.

  In the vibrato evaluation device according to a preferred aspect of the present invention, the output means calculates a straight line that approximates the time variation of the pitch fluctuation data, and the smaller the absolute value of the calculated slope of the straight line, the higher the evaluation. It may be calculated.

  In the vibrato evaluation apparatus according to a preferred aspect of the present invention, the output means calculates the standard deviation or standard error from the value of the pitch fluctuation range data, and the smaller the calculated standard deviation or standard error, the higher the evaluation. May be calculated.

  In the vibrato evaluation device according to a preferred aspect of the present invention, in the vibrato section, a zero-cross location specifying means for specifying a location where the value of the pitch difference value data changes from negative to positive or from positive to negative as a zero-cross location; And measuring means for measuring a time interval at which the zero-cross point specified by the zero-cross point specifying unit appears, and calculating a standard deviation or a standard error of the measured time interval, and the output unit includes: Higher evaluation may be calculated as the calculated standard deviation or standard error is smaller.

  The vibrato detection method according to a preferred aspect of the present invention includes a storage step of storing melody pitch data representing the pitch of a melody in a storage device, and detecting the pitch in units of frames of a predetermined time length from the sound data, A pitch detection stage for generating pitch data to represent, a filter processing stage for performing a filtering process to extract a specific frequency component on the pitch data generated in the pitch detection stage, and a melody pitch stored in the storage device A pitch represented by data is set as a zero reference value, and a value of pitch difference data representing a relative value between the pitch data filtered in the filtering step and the zero reference value is calculated. Zero-cross point identification stage that identifies a point that changes from negative to positive or positive to negative as a zero-cross point A step of specifying a section in which the zero-cross point specified in the zero-cross point specifying step is in a predetermined form; and specifying a time at which the pitch value is maximum and minimum in the pitch difference data; The pitch vibration width data is in a predetermined mode in the pitch vibration width data generation stage for generating pitch vibration width data from the difference between the maximum value and the minimum value to be generated, and in the section specified in the specific stage. And an output stage for outputting information indicating the section identified in the specific stage.

  The vibrato evaluation method, which is a preferred aspect of the present invention, stores a melody pitch data representing the pitch of a melody in a storage device, detects the pitch in units of frames of a predetermined time length from the sound data, and detects the detected pitch. A pitch detection stage for generating pitch data to be represented, a filter processing stage for applying a filtering process for extracting a specific frequency component to the pitch data generated in the pitch detection stage, and a reception stage for receiving data indicating a vibrato section In the vibrato section indicated by the data received in the receiving step, the pitch represented by the melody pitch data stored in the storage device is set as a zero reference value, and the pitch data filtered in the filtering step and the zero The pitch value of the pitch difference data that indicates the relative value to the reference value Calculating and specifying the time when the pitch difference data becomes maximum and minimum, and generating the pitch vibration width data from the difference between the adjacent maximum and minimum values, and the receiving step In the vibrato section indicated by the data received in step (b), a high evaluation is calculated when the pitch vibration width data is in a predetermined mode, and an output stage is provided for outputting the evaluation.

  A program according to a preferred embodiment of the present invention includes a computer that stores storage means for storing melody pitch data representing the pitch of a melody, and detects the pitch in units of frames of a predetermined time length from the sound data, and the pitch representing the detected pitch. A pitch detection means for generating data, a filter processing means for extracting a specific frequency component from the pitch data generated by the pitch detection means, and a melody pitch data stored in the storage means. The pitch to be represented is set as a zero reference value, and a value of pitch difference data representing a relative value between the pitch data filtered by the filter processing unit and the zero reference value is calculated. Zero cross point specifying means for specifying a point that changes from positive or positive to negative as a zero cross point; The specifying means for specifying the section in which the zero-cross location specified by the zero-cross location specifying means is in a predetermined form, and the time when the pitch value is maximum and minimum in the pitch difference data, and the adjacent maximum A pitch vibration width data generating means for generating pitch vibration width data from the difference between the value and the minimum value, and the pitch vibration width data in a predetermined mode in the section specified by the specifying means It is made to function as an output means which outputs the information which shows the area which the said specific means specified.

  According to another aspect of the program which is a preferred aspect of the present invention, the computer detects the pitch in units of frames of a predetermined time length from the storage means for storing the melody pitch data representing the pitch of the melody and the sound data. Pitch detection means for generating pitch data representing the pitch, filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means, and data indicating a vibrato section Pitch data represented by the melody pitch data stored in the storage means as a zero reference value in the vibrato section indicated by the data received by the receiving means and the receiving means, and the pitch data filtered by the filtering means; The pitch value of the pitch difference data representing the relative value with the zero reference value A pitch vibration width data generating means for specifying a time at which the pitch difference data becomes maximum and minimum, and generating pitch vibration width data from a difference between adjacent maximum values and minimum values; and the receiving means In the vibrato section indicated by the received data, a high evaluation is calculated when the pitch vibration width data is in a predetermined mode, and the data is made to function as output means for outputting the evaluation.

  According to the present invention, it is possible to detect a section in which the vibrato technique is used from the sound data, and further evaluate the skill of the vibrato technique in the section.

The karaoke apparatus 1 according to the present invention has a function of specifying a section to be sung in a music piece using a vibrato technique based on a singing voice (hereinafter, a model voice) as a model. Further, the karaoke apparatus 1 has a function of evaluating the skill of the vibrato technique particularly in the singing of a person who practices singing (hereinafter, a practitioner).
Embodiments of the present invention will be described below with reference to the drawings.

(A: Configuration)
FIG. 1 is a block diagram illustrating an example of a hardware configuration of a karaoke apparatus 1 according to the present embodiment.
In the figure, the control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory), and reads out and executes a control program stored in the ROM, thereby Each part of the apparatus 1 is controlled.

The display unit 13 includes a liquid crystal panel, and displays various images such as karaoke lyrics telop under the control of the control unit 11.
The operation unit 14 includes various operators, and outputs an operation signal indicating the operation content by the operator to the control unit 11.

The microphone 15 outputs an analog audio signal representing the collected audio.
The audio processing unit 16 includes an A / D converter, converts the audio signal output from the microphone 15 into digital audio data, and outputs the digital audio data to the control unit 11. The audio processing unit 16 includes a D / A converter, converts digital audio data received from the control unit 11 into an analog audio signal, and outputs the analog audio signal to the speaker 17.
The speaker 17 emits the audio signal received from the audio processing unit 16.

  The storage unit 12 is a storage unit for storing various data, and is, for example, a hard disk device. The storage unit 12 includes various storage areas described below.

In the accompaniment data storage area 121, accompaniment data representing accompaniment sounds of each music is stored. The accompaniment data is, for example, in a data format such as MIDI (Musical Instrument Digital Interface) format, and information indicating the pitch (pitch) of various musical instruments that accompany each of the above-mentioned music is written along with the progress of the music. The accompaniment data includes melody pitch data indicating the pitch of each guide melody note (note) of the music.
The lyrics data storage area 122 stores lyrics data indicating the lyrics of each song. The lyric data is displayed on the display unit 13 as a lyric telop as the music progresses during karaoke singing.
In the model voice data storage area 123, model voice data representing voice recorded in advance as a model for singing each music is stored. The model audio data is audio data in the WAVE format or MP3 (MPEG1 Audio Layer-3) format.

In the trainer voice data storage area 124, for each piece of music, voice data generated by the trainer's singing being picked up by the microphone 15 and converted into digital data by the voice processing unit 16 (hereinafter referred to as “practitioner voice”). Data) is stored. This trainer voice data is also voice data in the WAVE format or MP3 format.
The vibrato section data storage area 125 stores data (hereinafter referred to as vibrato section data) indicating sections in which the vibrato technique is used in the model voice data of each music piece. The vibrato section data is data generated by the control unit 11 as will be described later.
The parameter storage area 126 stores a pitch extracted from the model voice data or the trainer voice data and various parameters extracted from the pitch for each musical piece.

(B: Operation of the embodiment)
Next, the operation of the karaoke apparatus 1 according to the present invention will be described. In the following description, an operation in which the control unit 11 of the karaoke apparatus 1 specifies a vibrato section from the model voice and evaluates the skill of the vibrato technique in the specified section of the trainer voice data will be described.

(B-1; Karaoke accompaniment)
When the practitioner operates the operation unit 14 of the karaoke apparatus 1 and selects a song to sing, an operation signal specifying the selected song is output from the operation unit 14 to the control unit 11. The control unit 11 selects music according to the operation signal supplied from the operation unit 14, and performs the vibrato section specifying process shown in the flowchart of FIG. 2 for the selected music.

In step SA100, the control unit 11 displays the lyrics telop on the display unit 13 and performs karaoke accompaniment. That is, the control unit 11 reads the accompaniment data from the accompaniment data storage area 121 and supplies it to the audio processing unit 16. The audio processing unit 16 converts the accompaniment data into an analog audio signal and outputs it to the speaker 17. The speaker 17 emits the audio signal received from the audio processing unit 16. Further, the control unit 11 reads out the lyrics data from the lyrics data storage area 122 and causes the display unit 13 to display the lyrics telop according to the lyrics data.
The practitioner sings along with the karaoke accompaniment emitted from the speaker 17 while watching the lyrics telop displayed on the display unit 13. The trainee's song is picked up and trainer voice data is generated (step SA110). The generated trainer voice data is written in the trainer voice data storage area 124 of the storage unit 12.

The control unit 11 analyzes the pitches of the model voice data and the trainer voice data as the music progresses, and generates model pitch data and practitioner pitch data representing the analysis results (step SA120). That is, the model voice data corresponding to the selected music is read from the model voice data storage area 123, and the pitch is detected from the read model voice data in units of frames of a predetermined time length (for example, 10 msec). Then, the control unit 11 calculates a relative value when the pitch of the note included in the melody pitch data is set as a zero reference value from the detected pitch, and generates model pitch data. The generated model pitch data is written in the parameter storage area 126 of the storage unit 12.
Further, the control unit 11 detects the pitch in units of frames of a predetermined time length (for example, 10 msec) from the trainer speech data written in the trainer speech data storage area 124. Then, the control unit 11 calculates a relative value when the pitch of the note included in the melody pitch data is set as the zero reference value from the detected pitch, and generates the trainer pitch data. The generated trainee pitch data is written in the parameter storage area 126 of the storage unit 12.

  In FIG. 3, a part of the model pitch data generated as described above (time 12s000ms to 18s000ms) is shown by a graph A1. In FIG. 3, the horizontal axis represents time (elapsed time since the music was started). The vertical axis indicates the value of the model pitch data at each time. The trainer pitch data is also generated in the same manner as the model pitch data, but the illustration of the contents is omitted here.

  In step SA130, the control unit 11 determines whether or not the music performance has been completed for one song. If the determination result in step SA130 is “Yes”, the processes in and after step SA140 are performed. On the other hand, if the determination result in step SA130 is “No”, the processing from step SA100 to step SA120 is performed on the remaining portion of the music.

(B-2; identification of vibrato section)
When the performance of the music is finished, the control unit 11 specifies the vibrato section using the model pitch data.
In step SA140, the control unit 11 performs a filter process for extracting a specific frequency component on the model pitch data generated in step SA120. That is, the control unit 11 processes the model pitch data with a low-pass filter that extracts components having a frequency lower than 6 Hz, and generates new pitch data (hereinafter referred to as filter model pitch data). A graph A2 in FIG. 3 shows filter model pitch data obtained by processing the model pitch data by the low-pass filter.

  As shown in FIG. 3, the pitch data (for example, model pitch data; A1) before being filtered has a fine disturbance in the waveform. Such waveform disturbance is caused by, for example, reverb. When a pitch is detected from audio data subjected to reverberation, the detection result is not a sine wave but a waveform disturbance. For this reason, it has been difficult to accurately detect the vibrato section from the reverberated model voice. Furthermore, it is difficult to determine from the model voice data whether or not the model voice is reverberated. On the other hand, in the pitch data processed by the low-pass filter, the influence of the reverberation applied to the sound is removed, and this process makes it possible to appropriately specify the vibrato section in the process described later.

  In step SA150, the control unit 11 specifies a section (hereinafter referred to as a vibrato candidate section) indicating the characteristics of the vibrato section in the model voice data under the following conditions. That is, the control unit 11 identifies a point where the pitch represented by the filter model pitch data generated by applying the low pass filter in Step SA140 changes from negative to positive or from positive to negative (zero crossing) as a zero crossing point. Specifically, for example, in the example shown in FIG. 3, the time when the graph A2 representing the filter model pitch data zero-crosses, that is, the times P1, P2, P3, P4, etc., is specified as the zero-cross point.

  Next, the control unit 11 measures the time interval at which the zero-cross point appears, and the interval in which the measured time interval is within a predetermined range and the time interval is continuously detected a predetermined number of times or more, Identified as a vibrato candidate section. With this processing, in the example shown in FIG. 3, the section A3 in which the zero cross points appear at almost equal intervals is specified as the vibrato candidate section. In the section shown in FIG. 3, one section is specified as a vibrato candidate section, but a vibrato candidate section is specified also in a music portion not included in FIG. 3.

  Then, the control unit 11 extracts the following parameters for each of the vibrato candidate sections identified in step SA150 in order to more strictly analyze that the vibrato technique is actually used in the section (step SA160). ). In the following description, the number of vibrations per unit time is referred to as “vibrato frequency” when the value of the filter model pitch data periodically varies, for example, as in section A3 of FIG.

(1) Average frequency of vibrato (Af; Average of frequency)
The parameter Af is the average value of the vibration frequency of the vibrato in each vibrato candidate section, and is calculated as the average value of the reciprocal of the time interval at which the filter model pitch data zero crosses the horizontal axis.
(2) Standard deviation (Df: Deviation of frequency) of vibrato
The parameter Df is calculated as the standard deviation of the reciprocal distribution of the time interval at which the filter model pitch data crosses zero with the horizontal axis. From this parameter, it is possible to estimate the magnitude of “variation” of the vibrato frequency. That is, the closer the value of this parameter is to 0, the better the vibrato has a uniform frequency.

  Here, the “pitch vibration width” used in the description of the following parameters will be described. FIG. 4 is a graph showing the filter model pitch data (A2) extracted from FIG. In FIG. 4, the control unit 11 calculates the “pitch vibration width” of the vibrato candidate section as follows. First, the control unit 11 differentiates the filter model pitch data with respect to time, thereby specifying a maximum value and a minimum value from the graph of the data. For example, Q2, Q4, Q6, Q8, and Q10 in the figure indicate maximum values, and Q1, Q3, Q5, Q7, and Q9 indicate minimum values. The control unit 11 uses a difference between one specified local minimum value and a local maximum value that is temporally adjacent to the pitch vibration width as the pitch vibration width, and uses the pitch vibration width as a local minimum value and a local maximum value used to calculate the value. It is positioned at the time between. For example, the pitch vibration width W1 is generated from the minimum value Q1 and the maximum value Q2. In FIG. 4, pitch vibration widths W1 to W5 generated in this way are written.

Now, the description returns to the parameters extracted in step SA160.
(3) Average value of pitch vibration width (Ap: Average of pitch)
The parameter Ap indicates an average value of the pitch vibration width found in each vibrato candidate section. From this parameter, the vibration width of the pitch in the vibrato section can be estimated.
(4) Standard deviation of pitch vibration width (Dp; Deviation of pitch)
The parameter Dp indicates the standard deviation of the pitch vibration width found in each vibrato candidate section. From this parameter, the “variation” of the vibration width of the pitch in the vibrato section can be estimated. That is, the closer the value of this parameter is to 0, the better the vibrato that the pitch vibrates with a uniform vibration width.

(5) Slope of pitch (Sp; Slope of pitch)
The parameter Sp indicates the slope of the linear approximation line in the pitch vibration width graph. FIG. 5 shows an extracted graph of the pitch vibration width. The control unit 11 determines a linear approximation straight line for the pitch vibration width point in the vibrato candidate section (A3 in the figure). For example, in the section A3 shown in FIG. 5, the linear approximate straight line graph is determined as a straight line L1 and expressed as (Equation 1).
(Formula 1) P = 15t + 150
Thus, by calculating the linear approximate straight line, the slope Sp of the straight line is determined. In the above example, the slope Sp of the linear approximation line of the pitch vibration width is 15.
From this parameter, the stability of the vibration width of the pitch through the vibrato section can be estimated. In other words, the closer Sp is to 0, the better the vibrato is, in which the pitch fluctuation range is kept uniform throughout the vibrato section.

In step SA170, the control unit 11 determines whether to finally determine the vibrato candidate section identified in step SA150 as a vibrato section based on the following criteria. That is,
(1) Df is smaller than a predetermined threshold (2) Ap is within a predetermined range (3) Dp is smaller than a predetermined threshold (4) The absolute value of Sp is smaller than a predetermined threshold (1) to ( The section satisfying all the conditions of 4) is finally determined as the vibrato section.

  The above conditions (1) to (4) are optimum conditions for specifying the vibrato section. This is because, in general, in an ideal vibrato, the vibration frequency of the vibrato and the vibration width of the pitch do not vary and are uniform, and the vibration width is within a predetermined size range (for example, within 500 cents), This is because the fluctuation range of the pitch is constant throughout the vibrato section. Note that “cent” is a unit indicating a relative pitch difference of pitches. For example, a pitch indicated by +100 cents indicates a pitch that is a semitone above a reference pitch. The control unit 11 stores vibrato section data representing the specified section in the vibrato section data storage area 125. This completes the vibrato section specifying process.

  As described above, in step SA150, on the condition that the time interval of pitch vibration is within a predetermined range and that the time interval is continuously detected a predetermined number of times or more, the candidate for the vibrato section is once set. By narrowing down and precisely determining whether the vibrato candidate section is appropriate as the vibrato section based on the parameters extracted in step SA160, the vibrato section can be determined accurately.

(B-3; Evaluation of singing)
Hereinafter, a method for determining the skill of the vibrato technique of the corresponding trainer voice data for the vibrato section specified from the model voice data as described above will be described.

FIG. 6 is a flowchart showing the flow of the vibrato evaluation process in the practitioner's song.
In step SB100, the control unit 11 reads out the trainer pitch data from the parameter storage area 126, and performs a filtering process for extracting a specific frequency component in the same manner as the above-described filter model pitch data generation procedure. That is, the control unit 11 processes the trainer pitch data with a low-pass filter that extracts components in a frequency region lower than 6 Hz, and generates new pitch data (hereinafter referred to as filter trainer pitch data).

Next, the control unit 11 reads the vibrato section data generated by the vibrato section specifying process from the vibrato section data storage area 125 of the storage unit 12 (step SB110).
The control unit 11 extracts the following parameters in each of the vibrato sections of the filter trainer pitch data (step SB120). In addition, since it calculates in the procedure similar to the parameter demonstrated in the above-mentioned vibrato area identification process, the detailed description is abbreviate | omitted.

(1) Average frequency Af of vibrato
(2) Standard deviation Df of vibrato frequency
(3) Pitch vibration width average value Ap
(4) Standard deviation Dp of pitch vibration width
(5) Inclination Sp of linear approximation line of pitch vibration width

The control unit extracts the five parameters shown above for each vibrato section read in step SB110 and writes the extracted parameters in the parameter storage area 126.
In step SB130, the control unit 11 evaluates the skill of the vibrato technique in the vibrato section based on the parameters written in the parameter storage area 126. In this example, evaluation is performed using Df, Dp, and Sp. In addition, the evaluation result demonstrates the case where a point is deducted according to the value of the said parameter, for example from a perfect score (100 points).

The control part 11 makes a big deduction to singing evaluation, so that the value of Df is large. This is because Df represents a variation in the vibration frequency of vibrato, and is considered to be an excellent vibrato that shows a uniform vibration frequency as the value of Df is closer to zero.
Moreover, the control part 11 makes a big deduction to singing evaluation, so that the value of Dp is large. This is because Dp means the variation of the pitch fluctuation range in the vibrato section, and the closer the value of Dp is to 0, the better the vibrato that the pitch vibrates with a uniform fluctuation range.
Moreover, the control part 11 makes a big deduction to singing evaluation, so that the absolute value of Sp is large. Sp means the stability of the pitch vibration width through the vibrato section, and the closer the absolute value of Sp is to 0, the better the vibrato that the pitch vibration width is kept uniform throughout the vibrato section. Because it does.

  As described above, the control unit 11 evaluates the skill of the vibrato technique of the trainer voice data for each of the specified vibrato sections. In the vibrato technique, it is known that if the pitch vibration width is regular and within a certain range, the sound reverberantly becomes rich and desirable. Therefore, Df which is a parameter reflecting the uniformity of the vibration frequency of vibrato, Dp which is a parameter reflecting the uniformity of the fluctuation range of the pitch, and a parameter which reflects the uniformity of the vibration width of the pitch through the vibrato section It is possible to appropriately evaluate the skill of the vibrato technique based on the Sp.

(C: Modification)
As mentioned above, although embodiment of this invention was described, this invention is not limited to embodiment mentioned above, It can implement with another various form. An example is shown below.

(1) In the above-described embodiment, the case has been described in which the pitch is detected from the model voice data and the trainer voice data as the karaoke performance progresses, and the model pitch data and the practitioner pitch data are generated. However, this process does not necessarily have to be performed with the performance of karaoke. For example, the trainer voice data may be temporarily accumulated from the beginning to the end of the music, and the pitch may be detected from the model voice data and the practice voice data when the performance of karaoke is completed.

(2) In the above embodiment, the case where the vibrato section is specified from the model voice data has been described. However, the vibrato section may be generated from the model voice data in advance by the method described in the above embodiment, and karaoke music data including data indicating the specified section may be created. Therefore, the present invention can also be implemented as a device for generating karaoke music data that identifies a vibrato section using the above method.

(3) In the embodiment described above, the control unit 11 measures the time interval at which the zero-cross point appears in the filter sample pitch data, and the measured time interval is within a predetermined range, and the time interval is A case has been described in which sections continuously detected a predetermined number of times or more are specified as vibrato candidate sections. However, the vibrato candidate section may be specified based on a time interval in which the pitch is maximum or minimum, instead of the time interval at which the above-described zero-cross location appears. In short, any method capable of detecting the pitch vibration period may be used.

(4) In embodiment mentioned above, the control part 11 of the karaoke apparatus 1 specified the vibrato area after the karaoke accompaniment was complete | finished, and performed singing evaluation about the extracted area. However, the control unit 11 specifies the vibrato section by the method described in the above embodiment before the start of the karaoke accompaniment, and outputs information indicating the specified section to the display unit 13 and the speaker 17. A visual or audible signal may be presented to the practitioner from 17 so as to notify the vibrato section. That way, the practitioner can sing more carefully when the vibrato section is approaching.

(5) In the above-described embodiment, the case where the vibrato candidate section is specified in step SA150 and the vibrato section is specified based on the parameter for each of the specified vibrato candidate sections in step SA170 has been described. However, as described above, the vibrato section may be specified by using the conditions used in step SA150 to step SA170 at a time without narrowing down the vibrato section in two stages.

(6) In the embodiment described above, the melody pitch data indicating the pitch of each note (note) of the guide melody of the music is used. However, the melody pitch data is not limited to the data indicating the guide melody, and, for example, skill of singing is used. The melody pitch data prepared in advance for scoring may be used. In short, any data representing the melody pitch of the music may be used.

(7) In the above-described embodiment, the control unit 11 performs the low-pass filter process for extracting frequency components below a specific frequency. However, the filter process performed by the control unit 11 is not limited to this, for example, a predetermined frequency. A filter that extracts the frequency component of the width may be used. In short, any filtering process that extracts a specific frequency component may be used.

(8) In embodiment mentioned above, the case where the vibrato area was specified and the evaluation of singing was demonstrated about the model audio | voice data showing the audio | voice of a model, and the trainer audio | voice data showing the practitioner's song. However, the audio data to be processed is not limited to data representing the singing voice, and may be audio data representing the performance sound of a musical instrument such as a violin or a flute.

(9) The program executed by the control unit 11 of the karaoke apparatus 1 in the above embodiment is recorded on a recording medium such as a magnetic tape, a magnetic disk, a flexible disk, an optical recording medium, a magneto-optical recording medium, a RAM, and a ROM. Can be offered at. It is also possible to download to the karaoke apparatus 1 via a network such as the Internet.

(10) In the above embodiment, the method of specifying the vibrato section from the music using the model voice data is used. This is because, depending on the skill of the practitioner's vibrato, the vibrato section may not be specified from the practitioner's practitioner voice data. However, the vibrato section may be specified not from the model voice data but from the trainer voice data. By doing so, there is an effect that the singing evaluation is performed only on the part where the practitioner sang intentionally using the vibrato technique.

(11) In the above embodiment, the vibrato section is specified from the model voice with reverb applied. However, the control unit 11 can also specify the vibrato section from the model voice without reverb applied. . That is, according to the above-described embodiment, it is not necessary to determine whether or not reverberation is applied to the model voice regardless of whether or not the model sound is reverbed, and the vibrato section is specified from the model sound. can do.

(12) In the above embodiment, the case where the parameters of Af, Df, Ap, Dp, and Sp are calculated to specify the vibrato section and evaluate the singing has been described. Furthermore, the following parameters may be calculated and reflected in the above-described processing. For example, the value (Max / Min) of the ratio between the maximum value and the minimum value of the pitch in the parameter extraction interval may be obtained. Then, whether or not the calculated ratio value is smaller than a predetermined threshold value (k), that is,
1 <Max / Min <k
In the above-described vibrato section specifying process, if the determination result is affirmative, it may be determined that the section satisfies the conditions of the vibrato section. Further, in the above-described vibrato evaluation process, when the determination result is affirmative, points are added to the evaluation of the vibrato in the interval, and when the determination result is negative, the vibrato evaluation in the interval is deducted. May be.

(13) In the above embodiment, the case where the skill of the vibrato technique is evaluated by deducting from the perfect score (100 points) based on various parameters extracted from the filter trainer pitch data has been described. However, evaluation may be performed by adding points according to the values of the various parameters.

(14) In the vibrato technique, it is known that a desirable frequency varies depending on the pitch of the music portion on which the vibrato is made. For example, it is said that about 3 to 5 cycles per second is desirable for low sounds, and about 6 to 10 cycles is desirable for high sounds. In this way, when the desired frequency varies depending on the pitch, a table in which the pitch is associated with the desired vibrato frequency is provided, and the absolute value of the pitch extracted from the trainer voice data in the table is provided. Singing evaluation may be performed based on the difference between the attached vibration frequency and the vibration frequency of the vibrato in the trainee voice data.

(15) In the above embodiment, a case has been described in which various parameters are calculated from the filter practitioner pitch data, and the vibrato section specifying process and the vibrato evaluation process are performed using the calculated parameters in the above combinations. . However, the parameter combination method used for each process is merely an example, and it is not always necessary to use the combination as in the above-described embodiment. For example, the processing may be performed without using one or more parameters among the parameters used in the above-described embodiment, and other parameters may be used in combination.

(16) In the above embodiment, the case where the standard deviation Df of the vibrato frequency and the standard deviation Dp of the pitch vibration width are calculated in the parameter calculation has been described. However, the parameters may be parameters that reflect the degree of variation in the vibration frequency of the vibrato and the degree of variation in the pitch vibration width. Therefore, a standard error may be used instead of the standard deviation for calculating these parameters.

(17) In the above embodiment, a case has been described in which a vibrato section in each musical piece is specified and a song is evaluated for the specified vibrato section. However, when data indicating a vibrato section is obtained separately, the above-described vibrato section need not be specified. The case where the data indicating the vibrato section is obtained separately is, for example, the case where each piece of music data includes data indicating the vibrato section in advance. In such a case, the vibrato section indicated by the data indicating the vibrato section may be written in the vibrato section data storage area 125, and the written vibrato section data may be read and used during the vibrato evaluation process.

(18) In the above embodiment, as shown in the flowchart of FIG. 2, the vibrato section is specified (steps SA140 to 170) after the karaoke accompaniment and singing (steps SA100 to 120) are completed. explained. However, the vibrato section may be specified in real time as karaoke accompaniment and singing progress. The processing procedure of the control part 11 in that case is shown below. That is, the control unit 11 reads out model voice data as the karaoke accompaniment progresses, and generates model pitch data for the model voice data of the read portion. The control unit 11 specifies the vibrato section of the musical piece with the karaoke accompaniment by performing the processes of steps SA140 to 170 on the model pitch data sequentially generated as described above. As a result, the vibrato section is specified for all parts of the music at the end of the karaoke accompaniment.

It is a block diagram which shows the hardware constitutions of the karaoke apparatus. It is a flowchart which shows the flow of a vibrato area specific process. It is a figure which shows an example of the content of pitch data. It is a figure for demonstrating the calculation method of a pitch vibration width. It is a figure for demonstrating the calculation method of the linear approximate line of pitch vibration width. It is a flowchart which shows the flow of a vibrato evaluation process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Karaoke apparatus, 11 ... Control part, 12 ... Memory | storage part, 13 ... Display part, 14 ... Operation part, 15 ... Microphone, 16 ... Sound processing part, 17 ... Speaker, 121 ... Accompaniment data storage area, 122 ... Lyric data Storage area 123: Model voice data storage area 124 ... Trainer voice data storage area 125 ... Vibrato section data storage area 126 ... Parameter storage area

Claims (12)

Storage means for storing melody pitch data representing the pitch of the melody;
Pitch detection means for detecting pitch in units of frames of a predetermined time length from sound data and generating pitch data representing the detected pitch;
Filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means;
A pitch difference data value representing a relative value between the pitch data filtered by the filter processing means and the zero reference value, with the pitch represented by the melody pitch data stored in the storage means as a zero reference value A zero cross point specifying means for specifying a point where the pitch difference data changes from negative to positive or from positive to negative as a zero cross point;
A specifying means for specifying a section in which the zero-cross location specified by the zero-cross location specifying means is in a predetermined mode;
In the pitch difference data, the pitch vibration width data generating means for specifying the time at which the pitch value becomes maximum and minimum, and generating pitch vibration width data from the difference between the adjacent maximum value and minimum value;
Vibrato detection, comprising: output means for outputting information indicating the section specified by the specifying means when the pitch vibration width data is in a predetermined form in the section specified by the specifying means. apparatus. The specifying means measures a time interval at which the zero-cross location specified by the zero-cross location specifying means appears, the measured time interval is within a predetermined range, and the state is continuously repeated a predetermined number of times or more. The vibrato detection device according to claim 1, wherein the detected section is specified.   The output means calculates a straight line that approximates the time change of the pitch fluctuation width data in the section specified by the specifying means, and when the absolute value of the calculated slope of the straight line is smaller than a predetermined threshold, 2. The vibrato detection device according to claim 1, wherein information indicating the section specified by the specifying means is output.   The output means calculates the time average of the pitch fluctuation data in the section specified by the specifying means, and indicates the section specified by the specifying means when the calculated time average is within a predetermined range. The vibrato detection device according to claim 1, wherein information is output. Storage means for storing melody pitch data representing the pitch of the melody;
Pitch detection means for detecting pitch in units of frames of a predetermined time length from sound data and generating pitch data representing the detected pitch;
Filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means;
Receiving means for receiving data indicating a vibrato section;
In the vibrato section indicated by the data received by the receiving means, the pitch represented by the melody pitch data stored in the storage means is a zero reference value, and the pitch data filtered by the filtering means and the zero reference value The pitch value of the pitch difference data representing the relative value is calculated, the time when the pitch difference data becomes maximum and minimum is specified, and the pitch vibration is determined from the difference between the adjacent maximum and minimum values. Pitch vibration width data generating means for generating width data;
A vibrato section indicated by the data received by the receiving means; and an output means for calculating a high evaluation when the pitch vibration width data is in a predetermined mode and outputting the evaluation. Evaluation device.   The said output means calculates the straight line which approximates the time change of the said pitch fluctuation range data, and calculates high evaluation, so that the absolute value of the calculated inclination of the said straight line is small. Vibrato evaluation device.   6. The output means calculates a standard deviation or standard error from a value of the pitch fluctuation data, and calculates a higher evaluation as the calculated standard deviation or standard error is smaller. Vibrato evaluation device. In the vibrato section, a zero-cross location specifying means for specifying a location where the value of the pitch difference value data changes from negative to positive or from positive to negative as a zero-cross location;
A measuring means for measuring a time interval at which the zero-cross location specified by the zero-cross location specifying means appears, and calculating a standard deviation or a standard error of the measured time interval;
6. The vibrato evaluation apparatus according to claim 5, wherein the output unit calculates a higher evaluation as the standard deviation or standard error calculated by the calculation unit is smaller. Storing a melody pitch data representing a melody pitch in a storage device;
A pitch detection stage that detects pitch in units of frames of a predetermined time length from sound data, and generates pitch data representing the detected pitch;
A filter processing step of applying a filter processing to extract a specific frequency component to the pitch data generated in the pitch detection step;
The pitch represented by the melody pitch data stored in the storage device is set to a zero reference value, and the value of the pitch difference data representing the relative value between the pitch data filtered in the filtering process and the zero reference value A zero-cross point identifying step for identifying a point where the pitch difference data changes from negative to positive or from positive to negative as a zero-cross point;
A specifying step for specifying a section in which the zero-cross point specified in the zero-cross point specifying step is in a predetermined mode;
In the pitch difference data, the pitch vibration width data generation step of specifying the time when the value of the pitch becomes maximum and minimum and generating the pitch vibration width data from the difference between the adjacent maximum value and the minimum value;
An output stage that outputs information indicating the section specified in the specific stage when the pitch vibration width data is in a predetermined mode in the section specified in the specific stage. Method. Storing a melody pitch data representing a melody pitch in a storage device;
A pitch detection stage that detects pitch in units of frames of a predetermined time length from sound data, and generates pitch data representing the detected pitch;
A filter processing step of applying a filter processing to extract a specific frequency component to the pitch data generated in the pitch detection step;
A receiving stage for receiving data indicating a vibrato section;
In the vibrato section indicated by the data received in the receiving step, the pitch represented by the melody pitch data stored in the storage device is set as a zero reference value, and the pitch data and the zero reference value subjected to the filtering process in the filtering step The pitch value of the pitch difference data representing the relative value is calculated, the time when the pitch difference data becomes maximum and minimum is specified, and the pitch vibration is determined from the difference between the adjacent maximum and minimum values. Pitch vibration width data generation stage for generating width data;
In the vibrato section indicated by the data received in the receiving step, the vibrato section includes: an output step of calculating a high evaluation when the pitch vibration width data is in a predetermined form and outputting the evaluation. Evaluation methods. Computer
Storage means for storing melody pitch data representing the pitch of the melody;
Pitch detection means for detecting pitch in units of frames of a predetermined time length from sound data and generating pitch data representing the detected pitch;
Filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means;
A pitch difference data value representing a relative value between the pitch data filtered by the filter processing means and the zero reference value, with the pitch represented by the melody pitch data stored in the storage means as a zero reference value A zero cross point specifying means for specifying a point where the pitch difference data changes from negative to positive or from positive to negative as a zero cross point;
A specifying means for specifying a section in which the zero-cross location specified by the zero-cross location specifying means is in a predetermined mode;
In the pitch difference data, the pitch vibration width data generating means for specifying the time at which the pitch value becomes maximum and minimum, and generating pitch vibration width data from the difference between the adjacent maximum value and minimum value;
A program for functioning as an output means for outputting information indicating a section specified by the specifying means when the pitch vibration width data is in a predetermined mode in the section specified by the specifying means. Computer
Storage means for storing melody pitch data representing the pitch of the melody;
Pitch detection means for detecting pitch in units of frames of a predetermined time length from sound data and generating pitch data representing the detected pitch;
Filter processing means for applying a filter process for extracting a specific frequency component to the pitch data generated by the pitch detection means;
Receiving means for receiving data indicating a vibrato section;
In the vibrato section indicated by the data received by the receiving means, the pitch represented by the melody pitch data stored in the storage means is a zero reference value, and the pitch data filtered by the filtering means and the zero reference value The pitch value of the pitch difference data representing the relative value is calculated, the time when the pitch difference data becomes maximum and minimum is specified, and the pitch vibration is determined from the difference between the adjacent maximum and minimum values. Pitch vibration width data generating means for generating width data;
A program for calculating a high evaluation when the pitch vibration width data is in a predetermined form in the vibrato section indicated by the data received by the receiving means and functioning as an output means for outputting the evaluation.

Images