JP2019132980A - Karaoke device - Google Patents

Abstract

To provide a karaoke device capable of notifying a first singer and music suitable for karaoke singing in consideration of each user's mood when performing karaoke singing by a plurality of users.SOLUTION: The karaoke device includes a score storage unit which stores an emotional score indicating fun in association with each piece of music, an emotion analysis unit which analyzes the user's emotion based on the face image of the user, a singer identification unit which identifies a user who has the highest degree of feeling of emotion as a first singer based on a result of emotion analysis of each of a plurality of users, a recommended song specifying unit which specifies a song with the highest emotion score indicating fun as a recommended song for the first singer among sung songs included in the singing history of the first singer, and a notifying unit for notifying the first singer and the recommended song for the first singer.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a karaoke apparatus.

  When karaoke singing is performed by a plurality of users, they may refrain from each other, and it may take time to determine a user who performs karaoke singing first.

  Therefore, for example, in Patent Document 1, when the karaoke performance of the music is not started even after a predetermined time has elapsed after the first user logs in, the singing history of each user is referred to, the total number of singing times, and the predetermined time period. The technique of nominating the user who performs karaoke singing by using information such as the number of times of singing and the singing time is disclosed.

  Further, Patent Document 2 by the applicant discloses a technique for counting the number of times each user enters the room and making a reservation first, and specifying the user who has the highest number of reservations as the first singer. .

Japanese Patent Laid-Open No. 2006-114852 Japanese Patent Application No. 2006-150934

  Here, according to the technique of patent document 1 or patent document 2, the user (first singer) who performs karaoke singing first can be automatically appointed. On the other hand, each user may be fond of karaoke singing or may not be fond of karaoke singing depending on the physical condition of the day and the atmosphere of the place. However, according to the techniques of Patent Document 1 and Patent Document 2, even if the user is not comfortable with karaoke singing, there is a risk of being nominated as the first singer.

  In addition, a user who performs karaoke singing uses a remote control device or the like to select music and make a reservation. On the other hand, when the singer's nomination is made automatically as in Patent Document 1 and Patent Document 2, the user is suddenly assigned the singing order regardless of his / her intention, May be confused.

  An object of the present invention is to provide a karaoke apparatus capable of notifying the first singer and music suitable for karaoke singing in consideration of the mood of each user when performing karaoke singing by a plurality of users. There is to do.

The main invention for achieving the above object is a karaoke apparatus in which a plurality of users can perform karaoke singing in order, and the user feels when performing karaoke singing of the music for each music A score storage unit that associates and stores emotion scores indicating fun, an emotion analysis unit that performs emotion analysis of the user based on the face image of the user acquired by the imaging unit, and each of the plurality of users Based on the result of the emotion analysis, among the plurality of users, a singer identification unit that identifies a user having the highest degree of emotion indicating pleasure as the first singer, and the singing of the first singer Among the karaoke songs already included in the history, a recommended song identifying unit that identifies a song having the highest emotion score indicating the fun as a recommended song for the first singer, and the first song A singer in and the notification section for notifying the recommended music for the first singer, a karaoke apparatus having a.
Other characteristics of the present invention will be made clear by the description and drawings described later.

  According to the present invention, when performing karaoke singing by a plurality of users, it is possible to report the music suitable for the first singer and karaoke singing in consideration of the mood of each user.

It is a figure which shows the outline of the karaoke apparatus which concerns on 1st Embodiment. It is a figure which shows the hardware structural example of the karaoke main body which concerns on 1st Embodiment. It is a figure which shows the example of the table data memorize | stored in the score memory | storage part which concerns on 1st Embodiment. It is a figure which shows the emotion analysis result which concerns on 1st Embodiment. It is a figure showing a user's singing history concerning a 1st embodiment. It is a flowchart which shows the process of the karaoke apparatus which concerns on 1st Embodiment. It is a flowchart which shows the process of the karaoke apparatus which concerns on 2nd Embodiment.

<First Embodiment>
With reference to FIGS. 1-6, the karaoke apparatus which concerns on 1st Embodiment is demonstrated.

== Karaoke equipment ==
The karaoke apparatus 1 is an apparatus for performing karaoke performance and karaoke singing by a user. The karaoke apparatus 1 is installed in each room of a karaoke store, for example. Using one karaoke device, a plurality of users can perform karaoke singing in order. As shown in FIG. 1, the karaoke apparatus 1 includes a karaoke main body 10, a speaker 20, a display device 30, a microphone 40, a remote control device 50, and a photographing unit 60.

  The karaoke main body 10 performs various controls related to karaoke performance and karaoke singing, such as performance control of selected karaoke music, display control of lyrics and background video, and processing of audio signals input through the microphone 40. 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 a video or an image on the screen based on a signal from the karaoke main body 10. The microphone 40 is configured to convert a user's singing voice into an analog 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 photographing unit 60 is an apparatus for photographing a user's face and acquiring a face image (face image data). At least one photographing unit 60 is installed in a karaoke room where the karaoke apparatus 1 is installed. The imaging unit 60 outputs the acquired face image to the karaoke main body 10. There are various shooting timings by the shooting unit 60. For example, the imaging unit 60 performs imaging when the user performs a login operation using his / her user ID in the karaoke apparatus 1. The karaoke main body 10 stores the photographed face image in association with the user ID. Note that the photographing unit 60 may be provided in the remote control device 50, for example, or may be provided separately from the karaoke device 1.

== Karaoke body 10 ==
As shown in FIG. 2, the karaoke main body 10 according to the present embodiment includes a storage unit 10a, a communication unit 10b, an input unit 10c, and a control unit 10d. Each component is connected to the bus B via an interface (not shown).

[Storage unit]
The storage unit 10a is a large-capacity storage device that stores various data such as music data for performing a karaoke performance. A part of the storage area of the storage unit 10 a in this embodiment functions as the score storage unit 100.

(Score memory)
The score storage unit 100 stores, for each piece of music, an emotional score indicating the enjoyment felt by the user when performing a karaoke singing of the piece of music.

  Whether or not a user feels pleasant when performing a karaoke singing of a certain piece of music depends on known techniques relating to emotion analysis (for example, Japanese Laid-Open Patent Publication No. 10-187178 and “Speech Mind Analysis Service” (Hitachi Corporation). Systems)).

  For example, each time a new music piece is distributed, a server device (not shown) extracts an emotion feature quantity that correlates with how to put in emotion from the singing voice of a singer who sings the new music piece. Based on the extracted emotion feature quantity, the server device analyzes the emotion related to “fun” included in the singing. Then, the server device scores the information obtained by the emotion analysis (the higher the emotion related to “fun”, the higher the score), thereby generating a score related to “fun” of the new music. The server device distributes the generated score to the karaoke device 1 in association with the new music identification information (music ID). The score storage unit 100 of the karaoke apparatus 1 sequentially stores the distributed scores.

  FIG. 3 is a diagram illustrating a specific example of data stored in the score storage unit 100. In the example of FIG. 3, “fun” is shown as a score of 0 to 100 points. In the example of FIG. 3, an example is shown in which music is arranged and stored in descending order of score.

[Communication section, input section]
The communication unit 10b provides an interface for performing communication between the karaoke main body 10 and another configuration (or server device) of the karaoke apparatus 1. The input unit 10c is configured for a user to input various instructions. It is possible to input various instructions by selecting various icons displayed on the display screen of the display device 30 or the remote control device 50. In this case, the display device 30 and the remote control device 50 function as the input unit 10c.

[Control unit]
The control unit 10d performs various controls in the karaoke apparatus 1. The control unit 10d includes a CPU and a memory (both not shown). The CPU realizes various functions by executing programs stored in the memory. In the present embodiment, when the CPU executes a program stored in the memory, the control unit 10d functions as the emotion analysis unit 200, the singer identification unit 300, the recommended song identification unit 400, and the notification unit 500.

(Emotion Analysis Department)
The emotion analysis unit 200 performs emotion analysis of the user based on the user's face image acquired by the imaging unit 60.

  A publicly known technique can be used for the emotion analysis process using the face image (face image data). For example, according to “BeesightMARKII” (Arts Aihan Co., Ltd., “Beesight” is a registered trademark), six types of emotions can be analyzed from a human face image, and parameters for each emotion can be obtained. Further, according to a convolutional neural network (CNN / ConvNet) described in Japanese Patent Application Laid-Open No. 2017-156854, a specific emotion parameter can be obtained.

  The emotion analysis unit 200 analyzes the user's face image using these known techniques, and obtains a parameter relating to “joy” (a parameter relating to “happiness” in the case of BeesightMARK II). For example, the parameter may be obtained as a score of 0 to 100 points, or may be obtained as a 10-level score of 1 to 10.

  The emotion analysis unit 200 analyzes a face image for each of a plurality of users who use the karaoke apparatus 1 and performs emotion analysis of each user. The emotion analysis unit 200 outputs the analysis result to the singer identification unit 300 together with the user ID. For example, as a result of the emotion analysis on the face images of each of the users A to C, it is assumed that a parameter relating to “fun” is obtained as shown in FIG. 4 (FIG. 4 shows “fun” (Shown with a 10-point score). The emotion analysis unit 200 outputs each parameter to the singer identification unit 300 in association with the user ID.

(Singer specific part)
The singer identification unit 300 identifies, as the first singer, the user who has the highest degree of emotion indicating fun among the plurality of users, based on the emotion analysis results of the plurality of users.

  The degree of emotion indicating enjoyment corresponds to an analysis result (parameter) by the emotion analysis unit 200. For example, in the example of FIG. 4, the degree of emotion indicating the enjoyment of the user A is “9”, the degree of emotion indicating the enjoyment of the user B is “6”, and the enjoyment of the user C is indicated. The degree of emotion shown is “3”. In this case, the user A corresponds to “a user with the highest degree of emotion indicating fun”. Moreover, the first singer is a user who performs karaoke singing first (a user who performs karaoke singing first after entering the karaoke room) on the occasion of performing karaoke singing by a plurality of users.

  The singer specifying unit 300 specifies the first singer by comparing the results of emotion analysis of each user. For example, when the emotion analysis result as shown in FIG. 4 is obtained, the singer specifying unit 300 specifies the user A as the first singer. The singer identification unit 300 outputs the user ID of the identified first singer (user A) to the recommended song identification unit 400.

(Recommended music identification part)
The recommended song specifying unit 400 specifies a song having the highest emotion score indicating fun among the songs that have been karaoke sung included in the singing history of the first singer as a recommended song for the first singer.

  The singing history includes various data related to karaoke singing performed by a certain user in the past (music information sung in the past, etc.). The singing history is stored in, for example, a server device (not shown). The recommended music is music that recommends karaoke singing to the user.

  Here, it is assumed that user A is specified as the first singer as shown in the above example. In this case, the recommended music specifying unit 400 accesses the server device via the communication unit 10b and refers to the singing history of the user A. Here, it is assumed that the singing history of the user A includes data shown in FIG. 5 as music information (music ID) sung in the past. In this case, the recommended music specifying unit 400 compares the music included in the singing history of the user A and the music stored in the score storage unit 100, and the music included in the singing history of the user A (the user A karaoke A song that has been sung) and a song with the highest emotion score indicating fun (a song corresponding to ID-090 in FIG. 3) is identified as a recommended song.

  Note that the recommended music to be identified is not limited to one music. For example, when there are two or more songs included in the singing history of user A and two or more songs with the highest emotion score indicating fun (when there are multiple songs with the same emotion score), a plurality of songs are identified as recommended songs May be. Alternatively, for example, when a threshold of emotion score indicating fun (for example, score “90” or more) is determined in advance, and there are a plurality of songs exceeding the threshold among songs included in the user's singing history All of these music pieces may be specified as recommended music pieces.

  Moreover, when the user A performs login operation in the karaoke apparatus 1, a server apparatus reads the singing history of the user A, transmits to the karaoke apparatus 1, and memorize | stores it temporarily in the memory | storage part 10a of the karaoke apparatus 1. It may be left. In this case, the recommended music specifying unit 400 can specify the recommended music by referring to the singing history stored in the storage unit 10a.

(Notification part)
The alerting | reporting part 500 alert | reports the recommended music with respect to the first singer and the said first singer.

  Notification can be made in various ways. For example, the notification unit 500 causes the display screen of the display device 30 to display the name of the first singer and the song name and singer name of the song corresponding to the recommended song. Alternatively, the notification unit 500 may emit a message such as “Mr. ●●. Please sing and excite ●● (song name)” via the speaker 20.

  Further, the notification unit 500 may make a reservation for the recommended music after notifying the recommended music. For example, after notifying the recommended music to the user A, the notification unit 500 automatically reserves the karaoke performance reservation by automatically registering the music ID “ID-090” of the recommended music in the reservation queue. Can do.

== About processing in karaoke equipment ==
Next, a specific example of processing in the karaoke apparatus 1 according to the present embodiment will be described with reference to FIG. FIG. 6 is a flowchart illustrating a processing example in the karaoke apparatus 1.

  A plurality of users who have entered the karaoke room log in with their own user ID via the remote control device 50 or the like (login, step 10). The imaging unit 60 captures a logged-in user and acquires a face image.

  The karaoke apparatus 1 measures the elapsed time since all users logged in. If the music is not reserved even after a predetermined time has elapsed (Y in Step 11), the emotion analysis unit 200 determines the emotion of each user based on the user's face image acquired by the photographing unit 60. Analysis is performed (emotion analysis based on face image. Step 12).

  The singer identification unit 300 identifies, as the first singer, the user having the highest degree of emotion indicating fun among the plurality of users based on the result of the emotion analysis in step 12 (first singer). Step 13).

  The recommended music specifying unit 400 sets, as the recommended music for the first singer, the music having the highest emotion score indicating fun among the singing songs included in the singing history of the first singer specified in step 13. Identify (specify recommended music. Step 14).

  The alerting | reporting part 500 alert | reports the recommended music with respect to the first singer specified at step 13 and the first singer specified at step 14 (notification of the first singer and recommended music. Step 15).

  Note that the karaoke apparatus 1 may perform the processing from step 12 onward at a predetermined timing (for example, when the acquisition of each user's face image is completed) regardless of the elapsed time since login.

  As described above, the karaoke apparatus 1 according to the present embodiment captures, for each music piece, the score storage unit 100 that stores the emotion score indicating the enjoyment felt by the user when performing karaoke singing of the music piece in association with each other. Based on the user's face image acquired by the unit 60, the emotion analysis unit 200 that performs emotion analysis of the user, and based on the results of emotion analysis of each of the plurality of users, among the plurality of users, The singer identification unit 300 that identifies the user who has the highest degree of emotion indicating fun as the first singer, and the emotion that indicates fun among the songs that have been sung karaoke included in the singing history of the first singer The recommended music specifying unit 400 that specifies the music with the highest score as the recommended music for the first singer, and the recommended music for the first singer and the first singer are notified. It has a notification unit 500, a.

  According to such a karaoke apparatus 1, a user who has the highest degree of fun emotion can be identified as a singer based on the emotion analysis result using the face image. In general, when the degree of pleasure is high, it can be considered to be enthusiastic about karaoke singing. Therefore, it is unlikely that a user who is not interested in karaoke singing will be designated as the first singer. Moreover, even if it is a user suddenly nominated as the first singer by specifying a recommended song using the singing history of the specified singer, a song that can be sung by karaoke, and at that time Because music that matches the mood (fun mood) is recommended, you can enjoy karaoke singing without being confused by the selection. That is, according to the karaoke apparatus 1 according to the present embodiment, when performing karaoke singing by a plurality of users, the music suitable for the first singer and karaoke singing is notified in consideration of the mood of each user. be able to.

  Moreover, the alerting | reporting part 500 can reserve the said recommendation music, after alert | reporting a recommendation music. In this way, by automatically reserving the notified recommended music, the user designated as the first singer can smoothly perform karaoke singing without taking the trouble of performing reservation work.

<Second Embodiment>
Next, a karaoke apparatus according to the second embodiment will be described with reference to FIG. In the present embodiment, an example in which a new singer who performs karaoke singing after the first singer and a recommended tune for the new singer will be described using the result of emotion analysis. Detailed description of the same configuration as that of the first embodiment will be omitted.

(Singer specific part)
The singer identification unit 300 according to the present embodiment identifies the first singer and a new singer other than the first singer in descending order of the degree of emotion indicating fun based on the result of emotion analysis. .

  The new singer is a user other than the user specified as the first singer among a plurality of users who perform karaoke singing. For example, in the example of FIG. 4 of the first embodiment, the degree of emotion indicating the enjoyment of the user A is “9”, the degree of emotion indicating the enjoyment of the user B is “6”, and the user The degree of emotion indicating the enjoyment of C is “3”. In this case, the singer specifying unit 300 specifies the singer in descending order of the degree of emotion indicating fun. Specifically, the singer specifying unit 300 specifies the user A who is the “user with the highest degree of emotion indicating fun” as the first singer, and then uses the user B and the user other than the user A. About the person C, it specifies as a new singer in order with the high degree of the emotion which shows pleasure. Among the users B and C, the user who has a higher degree of emotion indicating fun is the user B. In this case, the singer specifying unit 300 specifies a new singer in the order of the user B and the user C. After user A is identified as the first singer, the emotion analysis of each user other than user A is performed after the first singer's karaoke song is being sung or after singing, and the fun at that time The singer may be specified by the degree of emotion indicating.

(Recommended music identification part)
The recommendation music specific | specification part 400 which concerns on this embodiment uses the music with the highest emotion score which shows fun among the music already completed in the karaoke song contained in the song history of a new singer as a recommendation music with respect to the said new singer. Identify.

  For example, assume that a new singer is identified in the order shown in the above example. In this case, first, the recommended music specifying unit 400 accesses the server device via the communication unit 10b and refers to the singing history of the user B. The recommended music specifying unit 400 compares the music included in the singing history of the user B with the music stored in the score storage unit 100, and the music included in the singing history of the user B (the user B has already singed the karaoke song). Music) and the music with the highest emotion score indicating fun are identified as recommended music. Next, the recommendation music specific | specification part 400 accesses a server apparatus via the communication part 10b, and refers the user C's singing log | history. The recommended music specifying unit 400 compares the music included in the singing history of the user C with the music stored in the score storage unit 100, and the music included in the singing history of the user C (the user C has already sung the karaoke song). Music) and the music with the highest emotion score indicating fun are identified as recommended music.

(Notification part)
After notifying the first singer and the recommended song for the first singer, the notifying unit 500 according to the present embodiment provides the new singer and the new singer in descending order of the feeling of fun. Notify recommended music.

  For example, the notification unit 500 causes the display screen of the display device 30 to display the name of the first singer (user A) and the song name and singer name of the song corresponding to the recommended song. Thereafter, the notification unit 500 displays the name of the user B who has the next highest degree of emotion after the user A and the song name and singer name of the song corresponding to the recommended song. Further, after displaying the name of the user B and the like, the notification unit 500 displays the name of the user C who has the highest degree of emotion next to the user C and the song name and singer of the music corresponding to the recommended music. Display the name.

  In addition, the timing which alert | reports the recommendation music with respect to a new singer and the said new singer may be any time, as long as it is after informing the recommendation tune with respect to the first singer and the said first singer. For example, the notification unit 500 may notify a new singer or the like when a recommendation tune is reserved after notifying the first singer and the recommended tune for the first singer. Or the alerting | reporting part 500 may alert | report new singers etc., after the karaoke song of the first singer is complete | finished.

== About processing in karaoke equipment ==
Next, a specific example of processing in the karaoke apparatus 1 according to the present embodiment will be described with reference to FIG. FIG. 7 is a flowchart showing a processing example in the karaoke apparatus 1.

  Steps 20 to 22 are the same as steps 10 to 12 of the first embodiment.

  Based on the result of the emotion analysis in step 22, the singer identification unit 300 identifies the singer in descending order of the degree of emotion indicating fun among the plurality of users (identifies the singer's order. Step 23). ).

  The recommended music specifying unit 400 first selects the music having the highest emotion score indicating fun among the songs already sung in the singing history of the first singer along the order of the singers specified in step 23. Is identified as a recommended song for the singer (recommended song of the first singer is identified. Step 24).

  The alerting | reporting part 500 alert | reports the recommended music with respect to the first singer who followed the order specified at step 23, and the first singer specified at step 24 (notification of the first singer and recommended music. Step 25).

  Next, the alerting | reporting part 500 alert | reports the recommended music with respect to the new singer (next singer) along the order specified at step 23, and the new singer specified at step 24 (new singer and recommendation). Notification of music, step 26).

  The notification unit 500 repeatedly performs notification processing until notification of all singers and recommended music is completed (Y in step 27).

  In addition, according to the structure of this embodiment, nomination will be made in order about all the users who are in a karaoke room. On the other hand, there are users who are reluctant to perform karaoke singing. Therefore, the singer specifying unit 300 may specify the singer only for users whose emotion analysis results are equal to or greater than a preset threshold. The threshold value is a reference value for determining whether or not to designate a karaoke song. For example, as shown in FIG. 4, if the degree of emotion indicating fun is shown in 10 levels, the threshold value is “ It can be indicated by a numerical value such as “5” or “6”. Moreover, the recommendation music specific | specification part 400 memorize | stores the identification information of the recommendation music when one user is specified as a singer. And when the same music is specified as the recommended music when other users are specified as singers, the recommended music specifying unit 400 selects the music with the highest emotion score indicating the next fun of the music. You may re-specify as a recommendation music with respect to another singer.

  As described above, the singer identification unit 300 according to the present embodiment identifies the users other than the first singer as new singers in descending order of the degree of emotion indicating fun based on the result of emotion analysis. And the recommendation music specific | specification part 400 specifies the music with the highest emotion score which shows pleasure among the music already performed in karaoke singing contained in the song history of a new singer as a recommendation music with respect to the said new singer, After notifying the recommended song for the first singer and the first singer, the notification unit 500 notifies the new singer and the recommended song for the new singer in descending order of the degree of emotion indicating fun. .

  According to such a karaoke apparatus 1, it is possible to specify a singer in descending order of the degree of fun feeling based on the emotion analysis result using the face image. Accordingly, an opportunity to perform karaoke singing in the order of higher degree of feeling of fun is obtained, so that the atmosphere of the place becomes easier to excite. Moreover, since the recommended music suitable for a singer is specified, karaoke singing can be enjoyed without being confused about music selection similarly to the karaoke apparatus 1 of 1st Embodiment.

<Others>
In the above embodiment, “fun” has been described as an example of the emotion score and emotion analysis. However, using emotions other than “fun” (or combining multiple emotions), singers and recommended songs It is also possible to specify. For example, in the case of a user who wants to sing a karaoke song to relieve stress, emotions indicating “sadness” and “anger” appear on the face. And the purpose of stress relief can be achieved by performing karaoke singing from a user with a high degree of emotion.

  For this reason, the score memory | storage part 100 links | relates and memorize | stores the emotion score which shows the sadness and / or anger which a user feels when performing the karaoke song of the said music for every music. The emotion analysis unit 200 performs emotion analysis on the sadness and anger of the user based on the face image of the user acquired by the photographing unit 60. Based on the results of the emotion analysis of each of the plurality of users, the singer specifying unit 300 selects the user who has the highest degree of feeling of sadness and / or anger among the plurality of users as the first singer. As specified. The recommended song specifying unit 400 specifies a song with the highest emotion score indicating sadness and / or anger among the songs that have been karaoke sung included in the singing history of the first singer as a recommended song for the first singer. To do.

  The above embodiment is presented as an example and does not limit the scope of the invention. The above configurations can be implemented in appropriate combination, and various omissions, replacements, and changes 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 equivalents thereof in the same manner as included in the scope and spirit of the invention.

DESCRIPTION OF SYMBOLS 1 Karaoke apparatus 100 Score memory | storage part 200 Emotion analysis part 300 Singer specific part 400 Recommended music specific part 500 Notification part

Claims (3)

A karaoke apparatus in which a plurality of users can perform karaoke singing in order,
A score storage unit that stores an emotional score indicating the enjoyment felt by the user when performing karaoke singing of the song for each song;
An emotion analysis unit that performs an emotion analysis of the user based on the face image of the user acquired by the imaging unit;
Based on the results of the emotion analysis of each of the plurality of users, a singer identifying unit that identifies a user who has the highest degree of emotion as a first singer among the plurality of users,
Among the songs that have already been sung karaoke included in the singing history of the first singer, a recommended song identifying unit that identifies a song having the highest emotion score indicating the fun as a recommended song for the first singer,
A notifying unit for notifying the recommended song for the first singer and the first singer;
Karaoke apparatus having The singer identification unit identifies the first singer and a new singer other than the first singer in descending order of the degree of emotion indicating fun based on the result of the emotion analysis,
The recommended song specifying unit specifies a song having the highest emotion score indicating fun among the songs already karaoke singing included in the singing history of the new singer as a recommended song for the new singer,
The notification unit notifies the recommended song for the first singer and the first singer, and then the recommendation for the new singer and the new singer in descending order of the degree of emotion indicating the fun. The karaoke apparatus according to claim 1, wherein music is notified.   3. The karaoke apparatus according to claim 1, wherein the notifying unit reserves the recommended music after notifying the recommended music. 4.

Images