JP7158282B2 - karaoke device - Google Patents

Description

The present invention relates to a karaoke machine.

A karaoke device is equipped with a scoring function that scores karaoke singing skill by comparing singing voice data extracted from singing voice input by a microphone with reference data indicating the main melody of a song played karaoke. there is

For example, in Patent Document 1, pitch data and tone length data are extracted from a singing voice signal input from a microphone in accordance with a karaoke performance, and are compared with a guide melody read out in parallel with the karaoke performance. Techniques for scoring and evaluating skill have been disclosed.

In addition, some singers imitate the singing of professional singers and sing using special singing techniques such as hiccups, falls, fists, and shouts. Patent Documents 2 to 5 disclose techniques for detecting such special singing techniques and evaluating singing.

JP-A-10-69216 JP 2005-107336 A JP 2008-225115 A JP 2008-268370 A Japanese Unexamined Patent Application Publication No. 2012-078701

By the way, there are techniques that have not been known in the past as techniques used to enhance the expressiveness of karaoke singing. If a singer uses such techniques, conventional karaoke machines cannot identify such techniques. Moreover, even though the singing technique gives the audience the impression that it is good, it was sometimes deducted by the conventional evaluation technique.

SUMMARY OF THE INVENTION An object of the present invention is to provide a karaoke apparatus capable of specifying whether or not karaoke singing includes pull-off singing (described later).

When the present inventor analyzed the singing pitch contained in the singing voice signal that was judged to be a special singing in terms of hearing, after maintaining the singing pitch at a certain height for a certain period of time, the singing pitch was lowered and the singing was performed in that state. It was found that the pitch was maintained for a certain period of time. Such a change is obtained, in particular, in the form of maintaining a singing pitch that is about the same as the pitch of a note to be sung for a certain period of time, then lowering the singing pitch, and then maintaining the singing pitch for a certain period of time in this state. be done. The present invention was completed based on this discovery, and is a technique that can identify this singing by detecting the pitch change unique to this singing.

It should be noted that this kind of singing is based on the pull-off method, which is a method of playing stringed instruments such as the guitar, in which the transition of the singing pitch is performed by pressing the fret with a certain string with the index finger and picking it, and then picking the same fret so that it leads to a lower note. A method in which the string is hooked with the ring finger to produce a sound)), so it is hereinafter referred to as "pull-off singing".

Specifically, the invention for achieving the above object is a singing pitch detection unit that detects a singing pitch for each predetermined section from a singing voice signal obtained by singing karaoke music, and , a pitch difference between two consecutive singing pitches is within a predetermined range, and a predetermined number or more of consecutive first horizontal sections and second horizontal sections, and from the singing pitch at the end of the first horizontal section to the A pull-off singing identification unit that identifies that a pull-off singing is being performed when there is a falling section in which the singing pitch drops under predetermined conditions until the singing pitch at the start of the second horizontal section exists. and a karaoke device. It is a karaoke device having
Other features of the present invention will be clarified by the description of the specification and drawings described later.

According to the present invention, it is possible to specify whether karaoke singing includes pull-off singing.

It is a figure which shows the hardware structural example of the karaoke apparatus which concerns on embodiment. It is a figure which shows the software structural example of the karaoke main body which concerns on embodiment. It is a flow chart which shows specific processing of a pull-off song concerning an embodiment. It is the figure which showed the singing pitch and pitch difference which concern on embodiment. It is the figure which showed the singing pitch and pitch difference which concern on embodiment. It is the figure which showed the relationship of the note of 1 which concerns on embodiment, and a singing pitch.

<Embodiment>
A karaoke apparatus 1 according to an embodiment will be described with reference to FIGS. 1 to 5. FIG.

==Karaoke Device==
The karaoke device 1 is a device for performing karaoke and singing karaoke by a singer. A karaoke device 1 registers karaoke songs selected by singers in a reservation queue and performs karaoke performances in order. As shown in FIG. 1, the karaoke device 1 includes a karaoke main body 10, a speaker 20, a display device 30, a microphone 40, and a remote control device 50. As shown in FIG.

The speaker 20 is configured to emit sound based on the sound emission signal from the karaoke main body 10 . The display device 30 is configured to display video and images on the screen based on the signal from the karaoke main body 10 . The microphone 40 is configured to convert a singer's singing voice (input voice to the microphone 40 ) into an analog singing voice signal and input it to the karaoke main body 10 . The remote control device 50 is a device for performing various operations on the karaoke main body 10 . The singer can use the remote control device 50 to select (reserve) a desired karaoke song. Icons and the like for inputting instructions for various operations are displayed on the display screen of the remote control device 50 .

The karaoke main body 10 performs various controls related to karaoke singing, such as performance control of selected karaoke music, display control of lyrics, background images, etc., and processing of singing voice signals input through the microphone 40 . As shown in FIG. 1, the karaoke main body 10 includes a control section 11, a communication section 12, a storage section 13, a sound processing section 14, a display processing section 15 and an operation section 16. FIG. Each configuration is connected to bus B via an interface (not shown).

The control unit 11 includes a CPU 11a and a memory 11b. The CPU 11a realizes various control functions by executing operation programs stored in the memory 11b. The memory 11b is a storage device that stores programs to be executed by the CPU 11a and temporarily stores various types of information during execution of the programs.

The communication unit 12 provides an interface for connecting the karaoke main body 10 to a communication line via a router (not shown).

The storage unit 13 is a large-capacity storage device that stores various data, such as a hard disk drive. The storage unit 13 stores a plurality of song data for karaoke performance by the karaoke apparatus 1 .

The song data is given a song ID for specifying each karaoke song. The music data includes accompaniment data, reference data, and the like. Accompaniment data is data that is the source of karaoke performance sounds. The accompaniment data includes information indicating the tempo for karaoke performance. A tempo is set to a predetermined value for each piece of music. Reference data is data used as a reference for scoring karaoke singing by singers. The reference data is composed of a plurality of notes (musical notes), and a predetermined pitch (reference pitch) is set for each note.

The storage unit 13 also stores lyrics telop data for displaying lyrics corresponding to each karaoke song on the display device 30 or the like, background image data such as a background image displayed on the display device 30 or the like during karaoke performance, Performance time data indicating karaoke performance time and music attribute information (information about the music such as singer name, lyricist/composer name, genre, etc.) are stored.

Under the control of the control unit 11 , the sound processing unit 14 controls performance of karaoke music and processes singing voice signals input through the microphone 40 . The display processing unit 15 performs processing related to various displays on the display device 30 and the remote control device 50 under the control of the control unit 11 . For example, the display processing unit 15 controls the display device 30 to display an image in which lyric telops and various icons are superimposed on a background image during performance of karaoke music. Alternatively, the display processing unit 15 causes the display screen of the remote control device 50 to display various icons for operation input. The operation unit 16 consists of a panel switch, a remote control receiving circuit, and the like, and transmits operation signals such as a music selection signal and a performance stop signal to the control unit 11 according to the operation of the panel switch of the karaoke device 1 or the remote control device 50 by the singer. Output. The control unit 11 detects an operation signal from the operation unit 16 and executes corresponding processing.

(software configuration)
FIG. 2 is a diagram showing an example of the software configuration of the karaoke main body 10. As shown in FIG. The karaoke main body 10 includes a singing pitch detecting section 100 , a pulling-off singing identifying section 200 , a pulling-off singing determining section 300 , a presenting section 400 and a scoring processing section 500 . The singing pitch detecting unit 100, the pulling-off singing identifying unit 200, the pulling-off singing determining unit 300, the presenting unit 400, and the scoring processing unit 500 are implemented by the CPU 11a executing a program stored in the memory 11b. .

[Singing pitch detector]
A singing pitch detection unit 100 detects a singing pitch for each predetermined section from a singing voice signal obtained by singing karaoke music.

Specifically, the singing pitch detection unit 100 analyzes the singing voice signal and detects the singing pitch. The singing pitch is detected in chronological order, one sample at a time, for example, in units of frames of a predetermined length of time (for example, 20 msec). The singing pitch detection section 100 sequentially outputs the detected singing pitches to the pull-off singing identification section 200 . Note that the detection of the singing pitch may be performed sequentially along with the singing of the karaoke music, or may be performed collectively after the singing of one karaoke music is completely finished. That is, in this embodiment, a frame with a time length of 20 msec corresponds to a predetermined section in singing pitch detection.

[Pull-off singing specific part]
The pull-off singing identification unit 200 detects, in the detected singing pitch, the pitch difference between two consecutive singing pitches within a predetermined range, and the first horizontal section and the second horizontal section that are continuous for a predetermined number or more. and a falling section in which the singing pitch falls under predetermined conditions from the singing pitch at the end of the first horizontal section to the singing pitch at the start of the second horizontal section. Identify that off-singing is being performed.

A horizontal section is a section in which the pitch difference between two consecutive singing pitches is within a predetermined range and which continues for a predetermined number or more. The predetermined range is an allowable range of deviation between two consecutive singing pitches for specifying a horizontal section. The predetermined number is the minimum required number of continuous singing pitches with a pitch difference within a predetermined range to specify the horizontal section. Arbitrary values are set in advance for the predetermined range and the predetermined number according to the extent of the specified pull-off singing. For example, the predetermined range is ±1 cent to ±10 cent and the predetermined number is 3-8.

The second horizontal section is a horizontal section specified later than the first horizontal section in singing of a certain karaoke piece. Note that the predetermined range and the predetermined number may differ between the first horizontal section and the second horizontal section.

The falling section is a section in which the singing pitch drops under a predetermined condition from the singing pitch at the end of the first horizontal section to the singing pitch at the beginning of the second horizontal section. The predetermined condition is a condition for identifying the descending section. As the predetermined condition, an arbitrary condition is set in advance according to the extent of the specified pull-off singing.

Here, with reference to FIGS. 3 to 4B, specific processing for pull-off singing will be described in detail. FIG. 3 is a flow chart showing processing for specifying a pull-off song. 4A and 4B are diagrams showing the singing pitch for each predetermined section detected by analyzing the singing voice signal obtained by singing the karaoke song X and the pitch difference between two consecutive singing pitches. In the examples of FIGS. 4A and 4B, the pitch difference is shown in cent values.

First, when the pitch difference between two consecutive singing pitches among the detected singing pitches is within a predetermined range and is continuous for a predetermined number or more, the pull-off singing identification unit 200 determines the pitch difference. is used as the singing pitch at the start of the first horizontal section (identification of the singing pitch at the start of the first horizontal section, step 10).

Specifically, the pull-off singing identifying section 200 obtains the pitch difference between two consecutive singing pitches, and determines whether or not the pitch difference is within a predetermined range. The predetermined range in this embodiment is assumed to be "±2 cents".

According to FIG. 4A, the pitch difference Pd(1) between the singing pitch P(1) and the singing pitch P(2) is "-13 cents". Here, it is assumed that Pd(1)=P(2)-P(1) is calculated, and the same applies to the following. In this case, the pull-off singing identification unit 200 determines that the pitch difference Pd(1) is not within the predetermined range. On the other hand, the pitch difference Pd(2) between the singing pitch P(2) and the singing pitch P(3) is "+2 cents". In this case, the pull-off singing identification unit 200 determines that the pitch difference Pd(2) is within a predetermined range. In this example, singing pitches before singing pitch P(2) are not considered.

The pull-off singing identifying section 200 sequentially obtains the pitch difference between two detected consecutive singing pitches, and determines whether or not it is within a predetermined range. At this time, the pull-off song identification unit 200 determines whether or not the pitch difference within a predetermined range continues for a predetermined number or more. If it continues for a predetermined number or more, the pull-off singing identification unit 200 sets the first singing pitch used when obtaining the pitch difference as the singing pitch at the start of the first horizontal section. The predetermined number in this embodiment is assumed to be "5".

According to FIG. 4A, five consecutive pitch differences within the predetermined range (±2 cents) range from the first pitch difference Pd(2) determined to be within the predetermined range to at least the pitch difference Pd(6). ing. In this case, the pull-off singing identification unit 200 sets the first singing pitch P(2) used when obtaining the pitch difference Pd(2) as the singing pitch at the start of the first horizontal section HZ1.

Next, when the pitch difference between two consecutive singing pitches is outside a predetermined range, the pull-off singing specifying unit 200 determines the singing pitch one before the last singing pitch used when obtaining the pitch difference. The first horizontal section is identified by taking the singing pitch at the end of the first horizontal section (identification of the first horizontal section, step 11).

Specifically, the pull-off song identification unit 200 determines whether or not the sequentially obtained pitch difference is outside a predetermined range. When the pitch difference is out of the predetermined range, the pull-off singing identification unit 200 shifts the singing pitch immediately before the last singing pitch used when obtaining the pitch difference that is out of the predetermined range to the first horizontal pitch. The first horizontal section is identified by taking the singing pitch at the end of the section.

According to FIG. 4A, the pitch difference Pd(n) is outside the predetermined range. In this case, the pull-off singing identification unit 200 sets the singing pitch P(n) immediately before the last singing pitch P(n+1) used when obtaining the pitch difference Pd(n) in the first horizontal section. The first horizontal section HZ1 is specified by setting it as the singing pitch at the end. That is, in the example of FIG. 4A, the first horizontal section HZ1 is from the predetermined section in which the singing pitch P(2) is detected to the predetermined section in which the singing pitch P(n) is detected.

After identifying the first horizontal segment, the pull-off song identifying unit 200 identifies the second horizontal segment in a similar manner.

That is, the pull-off singing identification unit 200 determines that, of the singing pitches detected after the singing pitch at the end of the first horizontal section, the pitch difference between two consecutive singing pitches is within a predetermined range, and If the number or more is continuous, the first singing pitch used to obtain the pitch difference is set as the singing pitch at the start of the second horizontal section (specifying the singing pitch at the start of the second horizontal section step 12).

Next, when the pitch difference between two consecutive singing pitches is outside a predetermined range, the pull-off singing specifying unit 200 determines the singing pitch one before the last singing pitch used when obtaining the pitch difference. The second horizontal section is identified by using the singing pitch at the end of the second horizontal section (identification of the second horizontal section, step 13).

Furthermore, if the pitch difference between the singing pitch at the end of the first horizontal section and the singing pitch at the start of the second horizontal section is equal to or less than a predetermined value, the pull-off singing identification unit 200 determines the first The section between the horizontal section and the second horizontal section is set as a descending section candidate (identification of descending section candidate; step 14).

The predetermined value is a value for determining whether the singing pitch in the second horizontal section is lower than the singing pitch in the first horizontal section. An arbitrary value is set in advance as the predetermined value according to the extent of the specified pull-off singing. The predetermined value is, for example, -40 cent to -120 cent. The predetermined value in this embodiment is assumed to be "-80 cent". A predetermined value is an example of a “predetermined condition”.

For example, assume that the pitch difference obtained by subtracting the singing pitch at the end of the first horizontal section HZ1 from the singing pitch at the beginning of the second horizontal section HZ2 is "-100 cents". In this case, the pitch difference is equal to or less than the predetermined value (-80 cent). Therefore, the pull-off song identification unit 200 determines the interval between the first horizontal interval HZ1 and the second horizontal interval HZ2 as the descending interval candidate DC.

Then, the pull-off song identification unit 200 determines that there are more than a certain number of continuous negative pitch differences between the start and end of the falling section candidate, and If the number of consecutive positive pitch differences up to the hour is less than a predetermined ratio, the descending segment candidate is identified as a descending segment (decision of descending segment; step 15).

The singing pitch at the start of the falling segment candidate corresponds to the singing pitch detected next to the singing pitch at the end of the first horizontal segment. Also, the singing pitch at the end of the falling segment candidate corresponds to the singing pitch detected immediately before the singing pitch at the start of the second horizontal segment. Also, the fixed number and the predetermined ratio are values for judging whether or not the segment determined as a descending segment candidate is actually a descending segment. Arbitrary values are set in advance for the fixed number and the predetermined ratio according to the extent of the specified pull-off singing. For example, the fixed number is 3-8, and the predetermined percentage is 10%-40% (of the total number of pitch differences included in the descending segment candidates). The fixed number in this embodiment is "6" and the predetermined ratio is "30%". A fixed number and a predetermined ratio are examples of a "predetermined condition."

According to FIG. 4B, among the 10 pitch differences Pd(n+1) to Pd(s−1) included in the descending section candidate DC, the number of negative pitch differences is "8". In addition, the ratio of pitch difference being positive is "20%". Therefore, the pull-off song identification unit 200 identifies the falling section candidate DC shown in FIG. 4B as the falling section DZ.

In this way, when the first horizontal section, the second horizontal section, and the descending section exist, the pull-off song identification unit 200 identifies that the pull-off song is being performed (the pull-off song identification, step 16). That is, the identified first horizontal section, second horizontal section, and descending section are singing sections by the pull-off singing.

[Pull-off singing judgment part]
The pull-off singing determination unit 300 determines the first horizontal position of the singing section by the specified pull-off singing in the period from the pronunciation start timing to the pronunciation end timing of one note included in the reference data of the karaoke song. If at least part of the section, all of the falling section, and at least part of the second horizontal section are included, it is determined that the pull-off singing for the one note has been performed.

The pronunciation start timing indicates the time at which pronunciation should be started when singing the note. The sounding start timing of a note corresponds to the elapsed time up to the note when the performance start point of the karaoke music is set to 0. The sounding end timing indicates the time at which sounding should end when the note is sung.

The pull-off singing determination unit 300 determines whether the pull-off singing specified by the pull-off specifying unit 200 is performed for one note.

Whether or not a certain pull-off song was performed for one note is determined by the first horizontal section of the singing section of the pull-off song during the period from the pronunciation start timing to the pronunciation end timing of the one note. A determination is made as to whether at least a portion, all of the descending section, and at least a portion of the second horizontal section are included.

FIG. 5 is a diagram showing the relationship between one note and singing pitch. In FIG. 5, the pitch of note N (reference pitch) is indicated by pitch Pn. Further, the start time Ts is the timing when the sound of the note N starts, and the end time Te is the timing when the sound of the note N ends. In FIG. 5, the vertical axis indicates the singing pitch and the horizontal axis indicates the time, but the horizontal axis may be interpreted as a continuous predetermined interval of 20 msec, and the singing pitch is detected for each predetermined interval.

As shown in FIG. 5, all of the first horizontal section HZ1, all of the falling section DZ, and all of the second horizontal section HZ2 are included between the start time Ts and the end time Te of the note N. (see FIG. 5(a)), if part of the first horizontal section HZ1, all of the descending section DZ, and all of the second horizontal section HZ2 are included (see FIG. 5(b)), the first includes all of the horizontal section HZ1, all of the descending section DZ, and part of the second horizontal section HZ2 (see FIG. 5(c)), or part of the first horizontal section HZ1, descending section DZ and part of the second horizontal section HZ2 (see FIG. 5(d)), the pull-off singing determination unit 300 determines whether the pull-off singing for note N is is determined to have been performed.

In addition, when the pull-off singing determination unit 300 further determines that the singing pitch included in at least a part of the first horizontal section is included in a certain range with respect to the pitch of one note, one It may be determined that the pull-off singing for the note has been performed. An arbitrary value is set in advance for the certain range according to the determination accuracy of the pull-off singing. For example, the fixed range is ±10 cents to ±50 cents relative to the pitch of the note. Alternatively, the fixed range can be a range above the pitch of the note (eg, from the pitch of the note to +30 cents) or below (eg, from the pitch of the note to -30 cents).

Various criteria can be used to determine whether the singing pitch included in at least part of the first horizontal section is included in a certain range with respect to the pitch of one note. For example, the pull-off singing determination unit 300 determines whether each singing pitch included in the first horizontal section is within a certain range, and a certain percentage or more (for example, 80% or more) falls within the certain range. If it is included, it is determined that the pull-off singing was performed. Alternatively, the pull-off singing determination unit 300 may obtain the average value of the singing pitches included in the first horizontal section and determine whether the average value is within a certain range.

In addition, when the entire first horizontal section is included in the period from the pronunciation start timing to the pronunciation end timing of one note, the pull-off singing determination unit 300 determines that all the singing included in the first horizontal section. It may be determined whether the pitch is included in a certain range, or it may be determined whether only a part of the singing pitch is included in the certain range.

[Presentation part]
The presentation unit 400 presents the determination result by the pull-off singing determination unit 300 to the singer. For example, when the determination result that the pull-off song for note N has been performed is input, the presentation unit 400 performs the pull-off song near the guide melody image corresponding to the note N displayed on the display device 30, for example. can be displayed. The guide melody image is displayed as an image of the melody of the karaoke song in order to support the karaoke singing of the singer. A known method can be used for displaying the guide melody image (see, for example, Japanese Patent Application Laid-Open No. 2004-205817).

Note that the presentation unit 400 can also display only an icon indicating that the pull-off singing has been performed, regardless of the guide melody image. Alternatively, the presentation unit 400 may notify that the pull-off singing has been performed by voice (applause, cheers, etc.) through the speaker 20 instead of displaying the icon indicating that the pull-off singing has been performed. good.

[Scoring section]
The scoring unit 500 compares a singing voice signal obtained by singing a karaoke song with reference data of the karaoke song, and calculates a score value. A known method can be used for the processing of calculating the score. For example, the grading processing section 500 performs grading processing for the accuracy of the singing pitch using the singing pitch based on the singing voice signal input from the microphone 40 and the reference pitch based on the reference data.

Here, the grading processing unit 500 according to the present embodiment, when the grading result of a certain note is determined to be unacceptable and when the pull-off singing for the certain note is performed, the grading result of the certain note is judged to pass. As shown in FIG. 5, the pull-off singing has a large deviation from the reference pitch of the notes, so there is a high possibility that it will be rejected according to the general scoring process. Therefore, even if the scoring result of a certain note is rejected, the scoring processing unit 500 determines that the pull-off singing was performed for the certain note by the pull-off singing determination unit 300. If so, the certain note is determined as a pass.

As is clear from the above, the karaoke apparatus 1 according to the present embodiment includes a singing pitch detection unit 100 for detecting a singing pitch for each predetermined section from a singing voice signal obtained by singing karaoke music, and a singing pitch detected by , the pitch difference between two consecutive singing pitches is within a predetermined range, and the first horizontal section and the second horizontal section that are continuous for a predetermined number or more, and the singing at the end of the first horizontal section If there is a falling section where the singing pitch falls under predetermined conditions from the pitch to the singing pitch at the start of the second horizontal section, pull-off specifying that singing is being performed. A song identification unit 200 is provided. According to such a karaoke device 1, it is possible to specify whether or not karaoke singing includes pull-off singing.

More specifically, if the pitch difference between two consecutive singing pitches among the detected singing pitches is within a predetermined range and is consecutive for a predetermined number or more, the pull-off singing identification unit 200 detects the pitch The first singing pitch used when obtaining the difference is the singing pitch at the start of the first horizontal section, and if the pitch difference between two consecutive singing pitches is outside a predetermined range, it is used when obtaining the pitch difference. The first horizontal section is specified by setting the singing pitch one before the last singing pitch to the singing pitch at the end of the first horizontal section, and after the singing pitch at the end of the first horizontal section Among the detected singing pitches, when the pitch difference between two consecutive singing pitches is within a predetermined range and is continuous for a predetermined number or more, the first singing pitch used when obtaining the pitch difference is the second If the pitch difference between two consecutive singing pitches is outside the predetermined range, the singing pitch one before the last singing pitch used to obtain the pitch difference is the singing pitch at the start of the horizontal section. The second horizontal section is specified by setting the singing pitch at the end of the second horizontal section, and the pitch between the singing pitch at the end of the first horizontal section and the singing pitch at the start of the second horizontal section. If the difference is equal to or less than a predetermined value, the interval between the first horizontal interval and the second horizontal interval is set as a descending interval candidate, and the continuous pitch difference between the start and end of the descending interval candidate is positive. If there are more than a certain number of falling section candidates, and the pitch difference that continues from the start time to the end time of the falling section candidate is less than a predetermined percentage, the falling section candidate is specified as the falling section. By the pull-off song identifying unit 200 executing such processing, it is possible to identify whether the karaoke song includes the pull-off song.

In addition, the karaoke device 1 according to the present embodiment, during the period from the pronunciation start timing to the pronunciation end timing of one note included in the reference data of the karaoke music, A pull-off singing that determines that a pull-off singing for one note is performed when at least part of one horizontal section, all of the falling section, and at least part of the second horizontal section are included. It has a determination unit 300 . According to such a karaoke apparatus 1, it can be determined whether or not singing of a certain note includes pull-off singing.

In addition, when the pull-off singing determination unit 300 further determines that the singing pitch included in at least a part of the second horizontal section is included in a certain range with respect to the pitch of one note, one It is also possible to determine that the pull-off singing to the note has been performed. According to such a karaoke device, it is possible to more accurately determine whether the singing of a certain note includes the pull-off singing.

Furthermore, the karaoke apparatus 1 according to the present embodiment passes the scoring result of a certain note when it is determined that the scoring result of the certain note is rejected and when the pull-off singing for the certain note is performed. It has a scoring processing unit 500 that determines that According to such a karaoke machine, it is possible to avoid scoring results that do not reflect the use of a singing technique called pull-off singing.

<Others>
Among the configurations of the control section 11 described in the above embodiment, at least the singing pitch detection section 100 and the pull-off singing identification section 200 are required to identify the pull-off singing.

Further, it is also possible to provide the pull-off song specifying process, determination process, and the like described in the above embodiment as a program. For example, the program causes a computer (for example, a karaoke device) to detect a singing pitch for each predetermined section from a singing voice signal obtained by singing karaoke music, and in the detected singing pitch, two consecutive A first horizontal section and a second horizontal section in which the pitch difference between the singing pitches is within a predetermined range and is continuous for a predetermined number or more, and the second horizontal section from the singing pitch at the end of the first horizontal section. If there is a falling section in which the singing pitch falls under predetermined conditions until the singing pitch at the start of , it is specified that the pull-off singing is being performed.

It is also possible to supply the program to the computer using a non-transitory computer readable medium with an executable program thereon storing the program. Examples of non-transitory computer-readable media include magnetic recording media (eg, flexible discs, magnetic tapes, hard disk drives), CD-ROMs (Read Only Memory), and the like.

The above embodiments are presented as examples and are not intended to limit the scope of the invention. The above configurations can be implemented in combination as appropriate, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. The above-described embodiments and modifications thereof are included in the invention described in the claims and their equivalents, as well as being included in the scope and gist of the invention.

1 karaoke device 10 karaoke main body 11 control unit 100 singing pitch detection unit 200 pull-off song identification unit 300 pull-off song determination unit 400 presentation unit 500 scoring processing unit

Claims (5)

A singing pitch detection unit that detects a singing pitch for each predetermined section from a singing voice signal obtained by singing karaoke music;
Among the detected singing pitches, a pitch difference between two consecutive singing pitches is within a predetermined range, and a predetermined number or more of consecutive first horizontal sections and second horizontal sections, and the first horizontal section From the singing pitch at the end of the second horizontal section to the singing pitch at the start of the second horizontal section, if there is a falling section in which the singing pitch falls under predetermined conditions, it is considered that the pull-off singing is being performed. a pull-off singing identification unit to identify;
A karaoke device having The pull-off singing identification unit,
Among the detected singing pitches, when the pitch difference between two consecutive singing pitches is within the predetermined range and is continuous for a predetermined number or more, the first singing pitch used when obtaining the pitch difference is the second 1 as the singing pitch at the start of the horizontal section,
When the pitch difference between the two consecutive singing pitches is outside the predetermined range, the singing pitch immediately before the last singing pitch used when obtaining the pitch difference is changed to the singing pitch at the end of the first horizontal section. Identify the first horizontal section by making it a singing pitch,
Of the singing pitches detected after the singing pitch at the end of the first horizontal section, if the pitch difference between two consecutive singing pitches is within the predetermined range and is continuous for a predetermined number or more, the The first singing pitch used when obtaining the pitch difference is the singing pitch at the start of the second horizontal section,
When the pitch difference between the two consecutive singing pitches is outside the predetermined range, the singing pitch immediately before the last singing pitch used when obtaining the pitch difference is set to the singing pitch at the end of the second horizontal section. Identify the second horizontal interval by being the pitch,
When the pitch difference between the singing pitch at the end of the first horizontal section and the singing pitch at the beginning of the second horizontal section is equal to or less than a predetermined value, the first horizontal section and the second horizontal section The section between is set as a descent section candidate,
Between the start and end of the descending section candidate, there are more than a certain number of consecutive negative pitch differences, and there is a continuous pitch difference between the start and the end of the descending section candidate. 2. The karaoke machine according to claim 1, wherein when the number of positive values is less than a predetermined percentage, the descending segment candidate is specified as the descending segment. At least part of the first horizontal section of the singing section by the specified pull-off singing in the period from the pronunciation start timing to the pronunciation end timing of one note included in the reference data of the karaoke song, A pull-off singing determination unit that determines that a pull-off singing has been performed for the one note when at least part of the falling interval and the second horizontal interval is included. 3. The karaoke apparatus according to claim 1 or 2. If the pull-off singing determination unit further determines that the singing pitch included in at least a part of the first horizontal section is included in a certain range with respect to the pitch of the one note, the one 4. The karaoke apparatus according to claim 3, wherein it is determined that the pull-off singing for the note of is performed. The present invention is characterized by comprising a grading processing unit that determines a grading result of a certain note as a pass when the grading result of a certain note is judged as failing and when the pull-off singing for the certain note is performed. 5. The karaoke apparatus according to claim 3 or 4, wherein:

Images