JP5585320B2 - Singing voice evaluation device - Google Patents

Description

  The present invention relates to a technique for outputting a result of evaluating a singing voice.

  In the karaoke device, a technique in which a song that a singer can sing is registered in advance, the highest and lowest sounds are detected from the guide melody data of the registered song, and the singer's singing range is displayed to inform the singer There is. (For example, patent document 1).

JP 2004-205818 A

In the technique disclosed in Patent Document 1, a song that can be sung by a singer is registered in advance, but since the singer performs judgment on the song that can be sung, whether or not the song is actually sung. It lacked accuracy. Also, even if a singer registers as a song that can be sung, it is unclear whether or not the song can be sung beyond the highest and lowest sounds of the song, and does not know the limits of its own singing range. Therefore, you have to sing a lot of songs, find a song that you can sing at the last minute, and register it.
An object of the present invention is to evaluate a singer's singing range without depending on the singer's own judgment.

  In order to solve the above-described problems, the present invention provides an acquisition means for acquiring a singing voice input during reproduction of music data, a pitch specifying means for specifying a singing pitch of the acquired singing voice, and an octave. A range specifying means for specifying a pitch range that is divided in units and to which the pitch of the acquired singing voice belongs, and for each component sound to be sung specified by the music data, the music The degree of coincidence of pitches when the specified pitch specified by the data is compared with the singing pitch and converted in octave units so that the specified pitch and the singing pitch belong to the same pitch range And calculating means for converting the designated pitch of the constituent sound to be sung in octave units so as to belong to the specified pitch range for the constituent sound, and based on the degree of coincidence calculated for the constituent sound Z And evaluation means for performing singing evaluation for the converted tone pitch Te provides a singing voice evaluation apparatus characterized by comprising an output means for outputting information corresponding to the result of the singing evaluation.

  Moreover, in another preferable aspect, the pitch specifying means analyzes the acquired singing voice by a first analysis method to specify the singing pitch, and the range specifying means includes the first analysis method and the first analysis method. Are analyzed by different second analysis methods to identify the pitch range.

  In another preferable aspect, the range specifying unit calculates a reliability that is an index of accuracy of the specified pitch range for the constituent sound to be sung, and the evaluation unit specifies the constituent sound. If the reliability of the pitch range is less than a predetermined threshold, the pitch range corresponding to the constituent sound before the constituent sound is equal to or higher than the threshold and the pitch range. The designated pitch is converted so as to belong to a pitch range determined based on a relationship with a pitch range to which a designated pitch of a previous constituent sound belongs.

  Moreover, in another preferable aspect, according to the result of the singing evaluation, further comprising a sound range specifying means for specifying a pitch of a certain range as a sound range of the singing voice, and the information output by the output means is the specified It is the range information which shows the selected range.

  According to the present invention, the singer's singing range can be evaluated regardless of the singer's own judgment.

It is a block diagram explaining the structure of the karaoke apparatus in embodiment of this invention. It is a functional block diagram explaining the structure of the song voice evaluation function in embodiment of this invention. It is a figure explaining the specific example of the coincidence degree calculation in the calculation part in embodiment of this invention. It is a flowchart explaining the operation | movement of the evaluation process in embodiment of this invention. It is a flowchart explaining operation | movement of the correction process in embodiment of this invention. It is a figure explaining the content of the evaluation result information in embodiment of this invention. It is a figure explaining an example of the display contents of the evaluation result in the embodiment of the present invention.

<Embodiment>
[Hardware configuration]
FIG. 1 is a block diagram illustrating a configuration of a karaoke apparatus 1 according to an embodiment of the present invention. The karaoke apparatus 1 is an example of a singing voice evaluation apparatus of the present invention, and is an apparatus that evaluates an input singing voice. The karaoke apparatus 1 receives the singing voice of the singer and evaluates the range of the singing voice. First, the hardware configuration of the karaoke apparatus 1 will be described.

  The karaoke apparatus 1 includes a control unit 10, an operation unit 20, a display unit 30, a communication unit 40, a storage unit 50, and an acoustic processing unit 60. Each of these components is connected via a bus. Moreover, the karaoke apparatus 1 has a speaker 61 and a microphone 62 connected to the acoustic processing unit 60.

  The control unit 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. The control unit 10 controls each unit of the karaoke apparatus 1 through the bus by executing a control program stored in the ROM or the storage unit 50. In this example, the control part 10 implement | achieves the song voice evaluation function for performing the evaluation of the sound range of the input song voice by running a control program.

The operation unit 20 is an operation device provided on an operation panel or the like, an operation button provided on a remote control, a keyboard, a mouse, or the like, and receives an operation of a singer and controls an operation signal indicating the contents thereof To the unit 10.
The display unit 30 is a display device such as a liquid crystal display, and displays contents according to the control of the control unit 10. The contents of this display are a background image, a lyrics telop, a menu screen, a singing voice evaluation result, etc. according to the progress of the karaoke music.
The communication unit 40 is connected to a communication line such as the Internet under the control of the control unit 10 and exchanges information with a communication device such as a server device. The control unit 10 may update information stored in the storage unit 50 using information acquired through the communication unit 40.
The memory | storage part 50 is memory | storage means, such as a hard disk and a non-volatile memory, and has a memory area | region which each memorize | stores music data, singing voice data, and evaluation result information.

The music data includes data related to the music to be sung in karaoke, and includes, for example, guide melody data (hereinafter referred to as GM data), accompaniment data, lyric data, and the like. The GM data is data indicating the melody of the vocal part of the music, that is, data in which the content of the constituent sound to be sung is designated, and is described in, for example, the MIDI (Musical Instrument Digital Interface) format. The accompaniment data is data indicating the contents of the accompaniment of the music and is described in, for example, the MIDI format. The lyrics data includes data indicating the contents of the lyrics of the music and data indicating the timing for changing the color of the lyrics telop displayed on the display unit 30. The music data may also include information defining the position of each constituent part of the music, such as the position of the chorus part of the music and the position of the melody start part.
The music data corresponding to the music specified by the operation of the operation unit 20 by the singer is read by the control unit 10, the karaoke accompaniment sound is output from the speaker 61, and the lyrics telop is displayed on the display unit 30. Used for.

The singing voice data is data indicating the singing voice input from the microphone 62 by the singer who sings the music that is the object of karaoke, and is stored in, for example, the WAVE format. The singing voice data stored in this manner is associated by the control unit 10 with music data indicating the music that is the target of karaoke.
The evaluation result information is information that is generated by the singing voice evaluation function and is used to evaluate the range of the singing voice (see FIG. 6). Specific contents will be described in the explanation of the singing voice evaluation function.

  The microphone 62 receives the singing voice of the singer and outputs an audio signal indicating the singing voice to the acoustic processing unit 60. The speaker 61 emits an audio signal output from the sound processing unit 60. The acoustic processing unit 60 includes a signal processing circuit such as a DSP (Digital Signal Processor), a sound source that generates an audio signal from a MIDI format signal, and the like. The sound processing unit 60 performs A / D conversion on the audio signal input from the microphone 62 and outputs it to the control unit 10. The sound processing unit 60 receives a MIDI signal based on music data from the control unit 10 and generates an audio signal based on the signal. The sound processing unit 60 performs signal processing such as effect processing and amplification processing on the audio signal thus generated, the audio signal output from the control unit 10, the audio signal input from the microphone 62, and the like, and then the speaker 61. Output to.

Here, the control unit 10 reads and reproduces the music data, acquires the audio signal output from the acoustic processing unit 60 during the period in which the accompaniment sound of the music is output from the speaker 61, and obtains the singing voice data. Generated and stored in the storage unit 50 in association with the music data.
The above is the description of the hardware configuration of the karaoke apparatus 1.

[Singing voice evaluation function]
Next, the singing voice evaluation function realized by the control unit 10 of the karaoke apparatus 1 executing the control program will be described. In addition, you may implement | achieve part or all of each structure in the song voice evaluation part 100 which implement | achieves the song voice evaluation function demonstrated below by hardware.

FIG. 2 is a functional block diagram illustrating the configuration of the singing voice evaluation unit 100 according to the embodiment of the present invention. The singing voice evaluation unit 100 includes an acquisition unit 110, a pitch specification unit 120, a range specification unit 130, a calculation unit 140, an evaluation unit 150, a range specification unit 160, and an output unit 170.
The acquisition unit 110 acquires the singing voice data of the portion corresponding to the singing voice in the predetermined evaluation period (in this example, the entire music piece) of the singing voice data stored in the storage unit 50, and the sound The data is output to the high specifying unit 120 and the range specifying unit 130.

The pitch specifying unit 120 specifies the pitch of the singing voice (hereinafter referred to as the singing pitch) for each constituent sound to be sung from the singing voice data acquired from the acquiring unit 110. Specifically, the pitch specifying unit 120 detects a zero cross when the waveform of the voice signal indicated by the singing voice data for each frame changes from negative to positive, and measures the time interval of the zero cross for each frame. Specify the singing pitch (frequency). At this time, a high-frequency component that becomes a noise component may be cut from the audio signal by a low-pass filter, or a DC component may be cut by a high-pass filter.
The pitch specifying unit 120 outputs information indicating the singing pitch specified in this way to the calculating unit 140 in time series.

  The range specifying unit 130 specifies the pitch range to which the singing pitch belongs from the singing voice data acquired from the acquiring unit 110. The pitch range indicates a range of pitches divided in octave units. The first pitch range, the second pitch range one octave above the first pitch range, and one octave above the second pitch range. The third pitch range, etc. is divided and each is defined by a frequency band.

  In this example, the pitch range is determined in correspondence with a MIDI note number (hereinafter referred to as a pitch name with an octave notation). For example, the third pitch range is considered to correspond to the frequency band from the lower limit of the frequency considered to be equivalent to “C3” to the upper limit of the frequency considered to be equivalent to “B3”, and the fourth pitch range is considered to be equivalent to “C4”. It is determined as a frequency band from the lower limit of the frequency to the upper limit of the frequency considered to correspond to “B4”. That is, a song whose pitch is “440 Hz” corresponding to “A3” is handled as belonging to the third pitch range. Note that, as long as it is divided in octave units, for example, a frequency band from a frequency considered to correspond to “A4” to a frequency considered to correspond to “A5” may be set as one pitch range.

The range specifying unit 130 performs as follows when specifying the pitch range to which the singing pitch belongs. First, the range specifying unit 130 performs FFT (Fast Fourier Transform) on the singing voice data acquired from the acquiring unit 110 to calculate a frequency spectrum for each frame. The range specifying unit 130 detects the first formant frequency from the calculated frequency spectrum, and specifies the pitch range corresponding to the frequency band including the first formant frequency as the pitch range to which the singing pitch belongs. At this time, the range specifying unit 130 calculates the accuracy of the detection result of the first formant frequency, that is, the reliability as an index of the accuracy of the specified pitch range. This reliability varies depending on the shape of the frequency spectrum. For example, the higher the peak level in the frequency spectrum, the higher the peak level, the higher the reliability. In this case, in the singing voice, the reliability is low in a portion that is a consonant or has a lot of noise.
The range specifying unit 130 outputs range information indicating the pitch range thus specified (hereinafter referred to as a specific pitch range) and the calculated reliability (hereinafter referred to as a calculated reliability) to the evaluation unit 150 in time series. To do.

In the range specifying unit 130, the singing pitch can be specified from the first formant frequency. However, since the calculation processing load increases in order to increase the accuracy, the accuracy is high enough to specify the pitch range here. The first formant frequency is detected by loosening. On the other hand, the pitch specifying unit 120 specifies the pitch from the zero cross of the voice waveform. In this detection method, the FFT processing in the range specifying unit 130 is used to determine which pitch is related to overtones. Specific accuracy is lower than that. On the other hand, in specifying the pitch from the zero cross, when the pitch is specified only in a frequency band within a certain pitch range, the specific accuracy is higher than that in the FFT processing.
In this example, the singing pitch and the pitch range are specified based on the pitches detected by the different detection methods in the range specifying unit 130 and the pitch specifying unit 120 in this way. On the other hand, for example, if the first formant frequency can be detected with high accuracy in the FFT processing, the singing pitch indicating the frequency of the first formant detected by the range specifying unit 130 is used instead of the pitch specifying unit 120. You may make it output to the calculation part 140. FIG.

  The calculation unit 140 acquires the information output from the pitch specifying unit 120 and the GM data stored in the storage unit 50. For each component sound to be sung in time series in the acquired GM data, the calculation unit 140 determines the pitch of the component sound (hereinafter referred to as a specified pitch) and the song specified by the pitch specifying unit 120. The degree of coincidence indicating the degree of coincidence of pitches is calculated by comparing with the pitches. The designated pitch may be indicated by a frequency, or may be indicated by a value corresponding to a note number such as “A4”.

Since the calculation unit 140 acquires the singing pitches in time series, the calculation unit 140 can identify the time-series correspondence between the constituent sounds specified in the GM data and the singing pitches. In addition, in calculating the degree of coincidence, the calculation unit 140 converts the designated pitch and the singing pitch so that the designated pitch and the singing pitch belong to the same pitch range, and compares the converted designated pitch with the singing pitch. To do. For example, if the singing pitch is 220 Hz (corresponding to “A2”), it belongs to the second pitch range, so that the pitches of the constituent sounds corresponding to the time series are converted to belong to the second pitch range (for example, If the designated pitch is “A3”, it is converted to “A2”) and then compared.
The calculating unit 140 determines the degree of coincidence information in which information indicating the calculated degree of coincidence (hereinafter referred to as a calculated degree of coincidence) is associated with information that can identify the constituent sound to be sung and its designated pitch. Output to. A specific example of processing in the calculation unit 140 will be described with reference to FIG.

FIG. 3 is a diagram illustrating a specific example of coincidence calculation in the calculation unit 140 according to the embodiment of the present invention. In FIG. 3, the horizontal axis indicates time, and the vertical axis indicates pitch. Each component sound to be sung designated by the GM data corresponds to a shaded square portion indicated by GM, and descriptions such as “C4” and “E4” indicate designated pitches of each component sound. The square part without diagonal lines is obtained by converting each constituent sound in octave units. The square range indicates the length of the constituent sound in the time direction. The pitch direction indicates a range of frequencies considered as the designated pitch, and is a range of ± 50 cent with the frequency of the designated pitch as the center.
The singing pitch specified by the pitch specifying unit 120 corresponds to the curve indicated by P.
N1, N2,... Described on the horizontal axis are represented in time series as portions corresponding to the period of each constituent sound, and hereinafter, the constituent sounds of the N1 portion will be referred to as constituent sounds N1 and the like. For example, the constituent tone N2 has a designated pitch “E4”.

  The calculation unit 140 compares the constituent pitch N1 with “C3” converted to one octave lower because the designated pitch is “C4” but the singing pitch is in the third pitch range. In this example, the calculation unit 140 matches the ratio of the period in which the singing pitch is included in the frequency ± 50 cent of “C3” with respect to the constituent sound N1 with respect to the constituent sound N1. It is calculated as a degree (70% in this example). In this example, the calculation unit 140 determines the degree of coincidence information in which the information indicating the constituent sound N1 and the designated pitch “C4” is associated with the information indicating the calculated degree of coincidence “70%”. 150.

  Returning to FIG. 2, the description will be continued. The evaluation unit 150 acquires the matching degree information output from the calculation unit 140 and the range information output from the range specifying unit 130, and performs an evaluation process for evaluating each pitch based on these information. . Hereinafter, the evaluation process will be described.

  FIG. 4 is a flowchart for explaining the operation of the evaluation process in the embodiment of the present invention. When the evaluation unit 150 acquires the matching degree information and the range information, the evaluation unit 150 starts the evaluation process. About the evaluation process demonstrated below, it is a process performed for every component sound which should be sung. Note that the evaluation unit 150 acquires the specific pitch range in time series, and each constituent sound is also shown in time series, so that the correspondence relationship between them can be identified.

  First, the evaluation unit 150 refers to the content indicated in the acquired matching degree information and range information, and various information on the specified pitch, the calculated matching degree, the specific pitch range, and the calculated reliability for the constituent sounds. Are stored in association with each other (step S110). The evaluation unit 150 stores up to a predetermined number of constituent sounds that are traced back by a predetermined number (for example, 20 sounds), and deletes the stored contents of constituent sounds before that. Note that the evaluation unit 150 may store all information about the first component sound of the music without deleting the stored content.

  Subsequently, the evaluation unit 150 determines whether or not the calculation reliability satisfies a predetermined condition (step S120). The predetermined condition is that the calculation reliability is equal to or higher than a predetermined threshold value. If the evaluation unit 150 determines that the calculation reliability does not satisfy the condition (step S120; No), the evaluation unit 150 performs a specific pitch range correction process (step S130). The specific pitch range correction process will be described with reference to FIG.

  FIG. 5 is a flowchart for explaining the operation of the correction processing in the embodiment of the present invention. The evaluation unit 150 refers to the content stored in step S110 corresponding to the past component sound, and acquires the calculation reliability for the component sound immediately before the component sound to be evaluated (step S210). The evaluation unit 150 determines whether or not the obtained calculation reliability satisfies a predetermined condition (step S220). This determination is the same as the determination in step S120. When the calculation reliability does not satisfy the condition (step S220; No), the evaluation unit 150 returns to step S210 again and continues the process. In other words, the evaluation unit 150 further acquires the calculation reliability for the immediately preceding constituent sound (step S210).

  If the calculated reliability satisfies the condition (step S220; Yes), the degree of deviation of the specific pitch range from the pitch range to which the specified pitch belongs is determined for the constituent sound satisfying the condition (step S220). S230). The degree of deviation is expressed in octave units. For example, if the designated pitch is “C4” and the specific pitch range is the third pitch range, the specific pitch range is shifted one octave below the fourth pitch range to which “C4” belongs. Therefore, the degree of deviation is represented as “−1”.

  The evaluation unit 150 sets the specific pitch range of the constituent sound that is the initial evaluation target (calculation reliability does not satisfy the condition) to the pitch range to which the designated pitch of the constituent sound belongs, in step S230. Is determined as a pitch range shifted by the degree of shift determined in (step S240). For example, on the premise of the above example, if the designated pitch for the component sound that is the initial evaluation target is “B3”, the second pitch range that is one octave below the third pitch range to which “B3” belongs. Is determined as the specific pitch range for the component sound, the content stored in step S110 is corrected, and the correction process is terminated. In this way, the specific pitch range stored in step S110 indicates any pitch range when the calculated reliability does not satisfy the condition, the pitch determined in step S240. Modified to range.

  If the calculation reliability satisfying the condition is not obtained even after returning to the first component sound of the music, a predetermined process may be performed. For example, the evaluation unit 150 determines the specific pitch range for the constituent sound to be evaluated as the pitch range to which the singing pitch specified by the pitch specifying unit 120 belongs, and corrects the content stored in step S110. Then, the correction process may be terminated.

Returning to FIG. 4, the description will be continued. When it is determined that the calculated reliability satisfies the condition (step S120; Yes) or when the correction process (step S130) is completed, the evaluation unit 150 refers to the content stored in step S110 and designates the specified pitch. Are converted in octave units so as to belong to the specific pitch range (step S140). At this time, if correction processing (step S130) has been performed, conversion is performed so as to belong to the specific pitch range after correction.
Then, the evaluation unit 150 records the calculated coincidence in the evaluation result information as a singing evaluation for the converted pitch (step S150), and ends the evaluation process for the constituent sounds. The evaluation unit 150 repeats these evaluation processes for all constituent sounds to be sung. Subsequently, the evaluation result information will be described with reference to FIG.

  FIG. 6 is a diagram for explaining the contents of the evaluation result information in the embodiment of the present invention. The evaluation result information is information in which an evaluation pitch, an evaluation score, and a calculated coincidence history are associated with each other, and indicates a result of singing evaluation for each pitch.

The evaluation pitch is a pitch to be evaluated. In this example, the evaluation pitch is determined corresponding to a MIDI note number.
The calculated coincidence history is the calculated coincidence recorded in step S150 of the evaluation process, and is recorded as a history corresponding to the evaluation pitch every time it is recorded as a singing evaluation with respect to the pitch. For example, in the example shown in FIG. 6, the evaluation pitch “D3” is in a state where the calculated coincidence is recorded four times.
The evaluation score is a score calculated according to the numerical value recorded in the calculated matching score history, and in this example, it is determined as the average of the scores in the calculated matching score history. For example, in the example shown in FIG. 6, for the evaluation pitch “C3”, the calculated coincidence records are “70” and “60”, so the average “65” is the evaluation score. This evaluation score calculation is performed by the evaluation unit 150 as a series of processes in step S150 of the evaluation process.

  In this way, the evaluation unit 150 evaluates the singing in units of pitches instead of evaluating the singing in units of constituent sounds by recording in the evaluation result information. That is, the evaluation score is a value that serves as an index of how well each pitch is sung.

Returning to FIG. 2, the description will be continued. The sound range specification unit 160 refers to the evaluation result information and specifies a certain range of pitches as the sound range of the singing voice (hereinafter referred to as a singing range). In this example, the range specifying unit 160 determines whether or not the evaluation score exceeds a predetermined passing score in order from the lowest evaluation pitch in the evaluation result information, and first exceeds the passing score. The evaluation pitch is detected as the lowest pitch. Further, the range specifying unit 160 determines whether or not the evaluation score exceeds a predetermined passing score in order from the highest evaluation pitch in the evaluation result information, and the evaluation sound that first exceeds the passing score is determined. High is detected as the highest pitch.
Then, the range specifying unit 160 specifies from the detected lowest range pitch to the highest range pitch as the singing range, and outputs information indicating the singing range to the output unit 170.

  The output unit 170 determines the content to be displayed on the display unit 30 as a display result based on the information output from the sound range specifying unit 160, and outputs a control signal for causing the display unit 30 to display the content. The content displayed on the display unit 30 may be anything that clearly indicates the lowest pitch and the highest pitch and indicates the singing range. The display content can be various, but as an example, the display content may be as shown in FIG.

  FIG. 7 is a diagram for explaining an example of display contents of evaluation results in the embodiment of the present invention. In this example, the display contents not only indicate the singer's singing range but also recommend the singer's singing range and how much the key can be shifted to sing. In performing such display contents, the output unit 170 detects the minimum pitch and the maximum pitch of the constituent sounds specified by the GM data. Then, the output unit 170 may calculate how much the key needs to be changed so that both the lowest pitch and the highest pitch are included in the singing range.

  In the example shown in FIG. 7, the singing range of the singer is an evaluation result in which the highest pitch is “C4” and the lowest pitch is “C3”. It is assumed that the musical pitch used for the evaluation has a maximum pitch “G4” and a minimum pitch “A3”. In that case, the output unit 170 lowers the sound range of the music and calculates the key change amount so as to be included in the singing sound range. In this case, it is included in the singing range by lowering it in the range of 6 to 8 semitones. In that case, the output unit 170 decides to recommend that the semitone is lowered by seven so that it is included in the central portion of the singing range, and the singing range, the range of the song, and the key change The range of the later music and recommended comments are displayed on the display unit 30.

  Thus, the karaoke apparatus 1 in the embodiment of the present invention can evaluate the singing range of the singer and display the content corresponding to the evaluation result on the display unit 30. The evaluation result of this singing range does not indicate the maximum range that can be sung by the singer, but indicates the maximum range that can be sung in accordance with the pitch to be sung even if there is an octave shift. Therefore, the singer can know the evaluation result of the singing sound range with high reliability.

<Modification>
As mentioned above, although embodiment of this invention was described, this invention can be implemented in various aspects as follows.
[Modification 1]
In the above-described embodiment, the karaoke apparatus 1 has evaluated the singing sound range by using the entire music as one evaluation period after the music is finished. You may evaluate in For example, the plurality of evaluation periods may be composition units of music, for example, a period corresponding to the first and second periods of the lyrics, or a period divided in fixed time units. Good.
In this case, the evaluation unit 150 may recognize and evaluate a plurality of evaluation periods by referring to the music data or measuring the time, and generate and record evaluation result information corresponding to each evaluation period.

[Modification 2]
In the embodiment described above, the output unit 170 outputs information for causing the display unit 30 to display information corresponding to the singing range specified by the range specifying unit 160 according to the evaluation result information. It is also possible to output to the display unit 30 information for displaying an evaluation score of each evaluation pitch shown in FIG. Also by this, the singer can know how much singing sound range his / her singing voice has.
The output unit 170 calculates a range evaluation point for the singing range based on the singing range specified according to the evaluation result information, and outputs information for displaying the range evaluation point to the display unit 30. You may make it do. This range evaluation point may be calculated based on a comparison result between the singing range and the musical range.
As described above, the output unit 170 may be any information as long as it outputs information to be displayed on the display unit 30 with contents corresponding to the evaluation result information.

[Modification 3]
In the embodiment described above, the range specifying unit 130 calculates the reliability with respect to the specified pitch range, but the reliability need not necessarily be calculated. In the case where the reliability is not calculated, the processing in steps S120 and S130 of FIG. 4 is unnecessary in the evaluation processing in the evaluation unit 150.

[Modification 4]
In the above-described embodiment, the threshold value used in the determination in step S120 in the evaluation process of the evaluation unit 150 is predetermined, but may be configured to be changeable. For example, when an instruction to change the threshold value is input by operating the operation unit 20, the control unit 10 may change the threshold value according to the instruction. Further, the threshold value may be changed according to the calculated coincidence calculated by the calculation unit 140 for the corresponding constituent sound. For example, the threshold may be increased if the calculated coincidence is low, and the threshold may be decreased if the calculated coincidence is high.
Note that threshold values used for various determination processes, such as a passing score used when the singing range is specified in the range specifying unit 160, may be configured to be changeable in the same manner as described above.

[Modification 5]
In the above-described embodiment, the evaluation score indicated in the evaluation result information is determined as the average of the scores in the calculation matching history, but may be determined by other calculation methods. For example, the highest score in the calculated coincidence history may be used as the evaluation score, and the lowest score may be used as the evaluation score. In this case, the evaluation unit 150 may not record the calculated matching degree as a history in the evaluation result information. For example, when using the highest score as the evaluation score, the evaluation unit 150 compares the evaluation score at the current time with the obtained calculated matching score, and calculates the matching score only when the calculated matching score is higher than the evaluation score. This is because it is only necessary to replace it every time.
Further, the evaluation unit 150 may determine an evaluation point based on an index (median value, mode value, etc.) obtained by performing statistical processing on the score recorded in the calculated matching score.

[Modification 6]
In the embodiment described above, the pitch range specifying unit 160 determines whether or not the evaluation score exceeds a predetermined passing score in order from the lowest evaluation pitch in the evaluation result information, and first exceeds the passing score. The detected evaluation pitch is detected as the lowest pitch, but may be detected by other determination methods. For example, the sound range specifying unit 160 may perform a calculation process such as a statistical process from the distribution of evaluation points with respect to the evaluation pitch indicated in the evaluation result information to specify the singing sound range. In the above description, the lowest pitch is described as an example, but the detection of the highest pitch can be similarly modified.

[Modification 7]
In the embodiment described above, the range specifying unit 130 may specify the pitch range using the singing pitch specified by the pitch specifying unit 120. In this case, the range specifying unit 130 acquires the information output from the pitch specifying unit 120, and the detected first formant frequency is any one of a frequency that is a fraction of the singing pitch and an integer multiple of the frequency. The pitch range may be determined based on the determination of whether or not the pitch is close.
For example, if the singing pitch specified by the pitch specifying unit 120 is 440 Hz, the range specifying unit 130 determines whether the first formant frequency is closer to 110, 220, 440, 880, or 1760 Hz. The pitch range may be determined. For example, if the first formant frequency is detected as 240 Hz, the range specifying unit 130 may specify the second pitch range that is the pitch range to which 220 Hz belongs because it is close to 220 Hz.

[Modification 8]
In the embodiment described above, the evaluation unit 150 determines the specific pitch range in step S240 as the pitch range corresponding to the degree of deviation determined in step S230, but according to the degree of deviation determined in another method. The pitch range may be determined. For example, in the embodiment, the evaluation unit 150 determines the degree of deviation of the specific pitch range from the pitch range to which the specified pitch belongs for one constituent sound that satisfies the condition. A plurality of extracted constituent sounds may be extracted, including constituent sounds that are traced back further, and the degree of deviation of the specific pitch range from the pitch range to which the specified pitch belongs may be determined for the extracted constituent sounds. . In this case, a plurality of degrees of deviation are obtained corresponding to each constituent sound, but the evaluation unit 150 may calculate the degree of deviation to be determined in step S230 based on the plurality of degrees of deviation. . For example, when the degree of the plurality of deviations is “−1”, “−1”, “−1”, “−2”, the average of these is “−1” rounded to an integer. Or the mode value “−1”.

[Modification 9]
In the embodiment described above, the information output from the output unit 170 is information for displaying the singing sound range on the display unit 30, but may be information indicating other contents. The information output from the output unit 170 may be information for notifying the singer of the evaluation result of the singing range, and may be, for example, voice data expressing the content of the evaluation result with a voice. Further, the information output from the output unit 170 may be MIDI format sequence data for sound generation using a sound source in the sound processing unit 60.

  In addition, as what alert | reports the evaluation result of a singing range to a singer, you may use light emission, a fragrance, a movement, etc. In this case, it is possible to perform a light emitting device using LEDs (Light Emitting Diodes) that emit light in various light emission modes, a scent discharge device capable of releasing gas having various scent components, and various operations. Connect the robot as an external device. Then, control data for controlling the external device in time series may be information output from the output unit 170.

[Modification 10]
The control program in the above-described embodiment is provided in a state stored in a computer-readable recording medium such as a magnetic recording medium (magnetic tape, magnetic disk, etc.), an optical recording medium (optical disk, etc.), a magneto-optical recording medium, or a semiconductor memory. Can do. Further, the karaoke apparatus 1 may download the control program via a network.

DESCRIPTION OF SYMBOLS 1 ... Karaoke apparatus, 10 ... Control part, 20 ... Operation part, 30 ... Display part, 40 ... Communication part, 50 ... Memory | storage part, 60 ... Sound processing part, 61 ... Speaker, 62 ... Microphone, 100 ... Singing voice evaluation part 110 ... Acquisition unit 120 ... Pitch identification unit 130 ... Range identification unit 140 ... Calculation unit 150 ... Evaluation unit 160 ... Sound range identification unit 170 ... Output unit

Claims (4)

Acquisition means for acquiring a singing voice input during reproduction of music data;
A pitch specifying means for specifying the singing pitch of the acquired singing voice;
Range specifying means for specifying a pitch range divided in octaves and to which the pitch of the acquired singing voice belongs,
For each constituent sound to be sung specified by the music data, the specified pitch specified by the music data is compared with the singing pitch, and the specified pitch and the singing pitch are the same pitch. A calculation means for calculating the degree of coincidence of pitches when converted in octave units so as to belong to the range;
The specified pitch of the constituent sound to be sung is converted in octave units so as to belong to the specified pitch range for the constituent sound, and the converted pitch is based on the degree of coincidence calculated for the constituent sound An evaluation means for performing singing evaluation;
The singing voice evaluation apparatus comprising: output means for outputting information corresponding to the result of the singing evaluation. The pitch specifying means specifies the singing pitch based on the pitch detected by the first detection method from the acquired singing voice,
The singing voice evaluation device according to claim 1, wherein the range specifying unit specifies the pitch range based on a pitch detected by a second detection method different from the first detection method. The range specifying means calculates a reliability that is an index of accuracy of the specified pitch range for the constituent sound to be sung,
When the reliability of the pitch range specified for the constituent sound is less than a predetermined threshold, the evaluation means determines that the reliability corresponding to the constituent sound before the constituent sound is the threshold. The specified pitch is converted so as to belong to the pitch range determined based on the relationship between the pitch range exceeding the value and the pitch range to which the specified pitch of the previous constituent sound belongs. The singing voice evaluation apparatus according to claim 1 or 2. According to the result of the singing evaluation, further comprising a range specifying means for specifying a certain range of pitches as the range of the singing voice,
The singing voice evaluation apparatus according to any one of claims 1 to 3, wherein the information output by the output means is range information indicating the specified range.

Images