JP7160064B2 - Karaoke device and program for singing evaluation - Google Patents

Description

TECHNICAL FIELD The present invention relates to a karaoke machine with which singing can be enjoyed, in particular, a karaoke machine with which singing can be evaluated, and a singing evaluation program that can be executed by various information processing apparatuses.

Traditionally, karaoke, in which people enjoy singing along with accompaniment, has been performed at social occasions and the like. Some karaoke machines used for karaoke have a scoring function for evaluating singing technique. The user can use the scoring function to grasp the degree of growth of his/her own singing, or compete with others for ranking.

Patent Literature 1 discloses a ranking providing method using a scoring function of a karaoke machine. In this ranking providing method, a first ranking is calculated based on a first parameter, and a second ranking smaller than the first parameter, such as a geographical attribute, an attribute related to a singer, or a date and time attribute. Calculate a second ranking by parameters and provide the results of the first ranking and the second ranking to the singer. With such a configuration, it is possible to provide singers with new interest in karaoke and to increase their motivation for ranking.

JP 2018-87995 A

Currently, the use of AI (Artificial Intelligence) is becoming active in many industries. The applicant is developing a singing evaluation using AI in view of the possibility of AI in karaoke singing evaluation. Here, when performing song evaluation by AI, there may be a difference between the score value and the conventional type of song evaluation. When switching to the song evaluation by AI, the user cannot know how far the new song evaluation method using AI deviates from the conventional song evaluation method.

Therefore, one of the objects of the present invention is to make the user aware of how much the new song evaluation method deviates from the conventional song evaluation method. In addition, when the new singing method and the conventional singing evaluation method are greatly different from each other, the user may be worried about which singing evaluation method is correct. Therefore, one of the objects of the present invention is to suppress the discrepancy between the new song evaluation method and the conventional song evaluation method as much as possible by performing appropriate correction.

Therefore, the karaoke apparatus according to the present invention employs the following configuration.
A karaoke device that performs singing evaluation based on a singing voice signal input from a microphone,
making it possible to execute a first evaluation process, a second evaluation process, and a notification process;
The first evaluation process evaluates the singing voice signal input from the microphone by a first evaluation method, calculates a first singing evaluation value,
The second evaluation process evaluates the singing voice signal input from the microphone by a second evaluation system different from the first evaluation system, and a second song evaluation having the same scale as the first evaluation process. Calculate the value of
The notification process notifies the first song evaluation value for the one singing voice signal and the difference value between the first song evaluation value and the second song evaluation value for the one singing voice signal.

Furthermore, in the karaoke device according to the present invention,
At least one of the first evaluation process and the second evaluation process calculates the first evaluation value or the second evaluation value after performing a correction process.

Furthermore, in the karaoke device according to the present invention,
The correction process in the first evaluation process calculates the first evaluation value based on a correction value based on the statistical information of the first song evaluation value and the statistical information of the second song evaluation value.

Furthermore, in the karaoke device according to the present invention,
The first evaluation method used in the first evaluation process is an evaluation method using AI.

Furthermore, in the karaoke device according to the present invention,
The second evaluation method used in the second evaluation process divides the same scale as that used in the first evaluation process into a plurality of scales for each of the plurality of singing elements, and sings with each scale for each of the plurality of singing elements. This is an evaluation method for calculating an evaluation value.

Furthermore, in the karaoke device according to the present invention,
Said 2nd evaluation process correct|amends for every said singing element.

Furthermore, in the karaoke device according to the present invention,
In the notification process, the song evaluation value for each of the plurality of song elements in the second evaluation process and the first song evaluation value are associated and notified.

Further, the singing evaluation program according to the present invention includes:
A song evaluation program executable by an information processing device,
making it possible to execute a first evaluation process, a second evaluation process, and a notification process;
The first evaluation process evaluates a singing voice signal input from a microphone by a first evaluation method, calculates a first singing evaluation value,
The second evaluation process evaluates the singing voice signal input from the microphone by a second evaluation method different from the first evaluation method, calculates a second singing evaluation value,
The notification process notifies the first song evaluation value and the difference value between the first song evaluation value and the second song evaluation value.

According to the karaoke apparatus or the song evaluation program according to the present invention, it is possible for the user to recognize the difference between the new song evaluation method and the conventional song evaluation method. Moreover, by performing appropriate correction, it is possible to suppress the deviation between the new song evaluation method and the conventional song evaluation method as much as possible, and to improve the reliability of both the song evaluation methods.

The figure which shows the structure of the karaoke system of this embodiment. A diagram showing various data configurations used in the karaoke system of the present embodiment. Flow diagram showing music playback processing of the present embodiment A diagram for explaining the correction (first correction) for the AI singing evaluation score of the present embodiment A diagram showing correction processing according to the present embodiment and various display items. Figure showing the song evaluation result screen of the present embodiment A diagram showing correction processing according to the present embodiment and various display items.

FIG. 1 is a diagram showing the configuration of a karaoke system according to this embodiment. The karaoke system in this embodiment includes a karaoke device 2 (also called a commander) and a remote control device 1 . The karaoke machine 2 and the remote control device 1 are connected for communication so as to form a network using the LAN 100 and the access point 130 .

A karaoke device 2 such as a karaoke box installed in a store includes an acoustic control section 25 as a playing section for playing music. The karaoke device 2 also includes an operation unit 21 that receives various inputs from the user. The karaoke device 2 includes an operation processing section 22 that interprets an input from the operation section 21 and transmits it to the CPU 30 . The karaoke machine 2 also includes a hard disk 32 as a storage section for storing various information. The karaoke machine 2 has a LAN communication section 24a as communication means for connecting to the LAN 100 and joining the network. The karaoke machine 2 of the present embodiment also includes a wireless LAN communication unit 24b, and instead of a wired network connection using the LAN communication unit 24a, a wireless network connection using the wireless LAN communication unit 24b can be performed. is also possible.

The karaoke machine 2 also has video reproducing means for displaying the lyric video and the background video on the monitor 41 . This video reproducing means includes a video reproducing section 29 for reproducing video based on video information, a video RAM 28 for temporarily storing the video to be reproduced, a video for superimposing lyric telops on the reproduced video, imparting video effects, etc. It is configured with a control unit 31 .

Furthermore, in this karaoke apparatus 2, various information can be displayed on a touch panel monitor 33 in addition to the monitor 41 connected to the outside. The touch panel monitor 33 includes a display section 35 for displaying video information input from the video control section 31 and a touch panel 34 for outputting the position of touch input to the operation processing section 22, which are superimposed. The touch panel monitor 33 is arranged on the front surface of the housing of the karaoke machine 2 or the like, and functions as an input section like the operation section 21 of the karaoke machine 2 or the touch panel monitor 11 of the remote control device 1 or the like. By selecting a piece of music on the touch panel monitor 33, the user can perform various operations on the karaoke device 2, such as making the karaoke device 2 make a reservation directly.

Further, the karaoke machine 2 comprises a control section including a CPU 30 for centrally controlling each component and a memory 27 for temporarily storing information necessary for executing various programs.

With such a configuration, the karaoke device 2 executes various types of processing, and the main functions of the karaoke device 2 are music reservation processing, music reproduction processing, and the like. The music reservation processing is processing for designating and reserving music based on designation from the user, and is executed in cooperation with the remote control device 1 . The reservation information formed by the music selection process of the remote control device 1 is transmitted to the karaoke device 2 . The karaoke machine 2 registers the received reservation information in the reservation table in the memory 27. - 特許庁The music reproduction process is a process of reproducing the reserved music, and is a process in which the music performance process and the lyric display process are executed in synchronization.

The music playing process is a process of causing the sound control section 25 to perform a musical performance based on the performance information included in the music information. The music played by the sound control unit 25 is emitted from the speaker 42 together with the singing voice input from the microphones 43a and 43b. The lyric display process is a process for assisting singing by displaying the lyric information included in the music information on the monitor 41 . A background image display process may be executed in which a background image is superimposed on the lyrics displayed in the lyrics display process.

On the other hand, the remote control device 1 can execute music selection processing of searching for music based on an instruction from the user and transmitting reservation information to the karaoke device 2 for the music for which a reproduction instruction has been given. Further, the remote control device 1 can receive various information from the karaoke device 2 or the server device 5 connected to the Internet and execute various processes. In this embodiment, an operation unit 17 and a touch panel monitor 11 are provided as user interfaces for receiving various instructions from the user. The touch panel monitor 11 includes a display section 11a and a touch panel 11b, and displays various interfaces on the display section 11a and can receive touch input from the user.

Furthermore, the remote control device 1 has a memory 14 as a storage unit for storing a database required for music selection processing, various programs, and various information generated along with the execution of the programs, and a memory 14 for collectively controlling these components. and a remote controller side control unit. The controller on the remote control side includes a CPU 15, an image control unit 13 for forming an image to be displayed on the touch panel monitor 11, a video RAM 12 for temporarily storing image information to be displayed, and an input from the touch panel monitor 11 or the operation unit 17. and an operation processing unit 18 for transmitting to the CPU 15.

The remote control device 1 is wirelessly connected to the access point 130 by the wireless LAN communication unit 16 , thereby being connected to the network formed by the LAN 100 . Each remote control device 1 is associated with a specific karaoke device 2 in advance. Various commands output from the remote control device 1 are received by the associated karaoke device 2 .

With such a configuration of the remote control device 1, various inputs from the user are received from the touch panel monitor 11 or the operation unit 17, and video information is displayed on the touch panel monitor 11 to provide various information to the karaoke device 2. It is possible to perform various processes such as music selection processing for transmitting reservation information to be output.

FIG. 2 is a diagram showing the data structure of music information according to this embodiment. The music information includes meta information including various information related to the music information, and real information for performing various processes such as performance and display of lyrics. The meta information includes music IDs for identifying music information, music-related information such as music titles, singer names, and genres. The music-related information can be used as search target items when the user searches for music. The actual information of the music information includes performance information, lyric information, background image information, and the like.

The performance information is information for playing accompaniment sounds for karaoke, which includes control information for electronic musical instruments based on the MIDI standard, or compressed audio information obtained by recording an actual performance. The lyric information is information displayed in synchronism with the performance information in order to assist singing, and may be configured to change the color of the displayed lyric in synchronism with the performance. The song evaluation information is information for evaluating the user's singing voice at the time of music reproduction, and includes a melody to be sung. When performing song evaluation during music reproduction, it is possible to calculate score values and the like by comparing the singing voice input to the microphones 43a and 43b with this song evaluation information.

In the music reproduction process of this embodiment, it is possible to perform two types of song evaluation at the same time. The first is standard song evaluation processing (corresponding to "second evaluation processing" according to the present invention) that has been conventionally performed. This standard song evaluation process is a process of performing scoring using an evaluation method in which the song evaluation information in the song information is compared with the singing voice input to the microphones 43a and 43b. This standard singing evaluation process is a process of executing an evaluation method of calculating a total score by calculating a score for each singing element in comparison with the singing evaluation information serving as a reference and totaling the scores for each singing element. . In this embodiment, the three elements of pitch, rhythm, and singing technique will be described as an example. However, it does not have to be three elements, and these three elements may be further subdivided or integrated.

On the other hand, the second is the newly introduced AI song evaluation process (corresponding to the "first evaluation process" according to the present invention). The AI song evaluation process is a process of performing scoring using an evaluation method using artificial intelligence (AI). The AI singing evaluation process receives music information and various parameters extracted from the singing voice, learns in advance the goodness of the song that people feel (song goodness of the human feeling), and the music information played this time, Then, it is a process of calculating a score as a song evaluation by evaluating various parameters extracted from the current singing voice based on the learning result. According to such an AI song evaluation process, it is possible to perform a song evaluation equivalent to the evaluation of the goodness of a song performed by a person. Also, currently, the AI song evaluation process only calculates the score of the entire song (total score), and cannot calculate the score for each song element like the standard song evaluation method.

Specifically, the AI singing evaluation process is a process specialized in comprehensively evaluating feature amounts (parameters) relating to the goodness of a song that people perceive. Therefore, in the AI singing evaluation process, the score is calculated by evaluating the singing overall instead of scoring each singing element such as pitch and rhythm. A score based on the evaluation method is calculated. However, since both the standard song evaluation process and the AI song evaluation process calculate the evaluation results out of 100 points, the scale of the evaluation results is the same even if the evaluation methods are different. Therefore, they do not have the same evaluation score.

Now, a description will be given of music playback processing for performing such two types of song evaluation. FIG. 3 is a flowchart showing music reproduction processing according to this embodiment. In the karaoke device 2, music is reserved based on the operation of the remote control device 1 or the input unit such as the touch panel monitor 33 or the like. When a song is reserved, reservation information including a song ID for identifying the song information, the user ID of the user who made the reservation, and the like is registered in a reservation table stored and managed in the memory 27 of the karaoke device 2 .

The karaoke machine 2 first checks the reservation table to confirm the music to be reproduced (S101). If there is a song to be played next (S102: Yes), the song information corresponding to the song ID in the reservation information is read and playback of the song is started (S103). AI song evaluation processing (S104) and standard song evaluation processing (S105) are executed during the reproduction period of the music information. In this embodiment, the AI song evaluation process (S104) and the standard song evaluation process (S105) are both calculated with the same scale (in this embodiment, the maximum score is 100 points).

When the music has finished playing (S106: Yes), the AI singing evaluation score (corresponding to the "first singing evaluation value" according to the present invention), which is the evaluation result of the AI singing evaluation process, and the evaluation result of the standard singing evaluation process (S107). Here, A is the AI singing evaluation score, and B is the standard singing evaluation score.

FIG. 4 is a diagram for explaining the correction (first correction) for the AI singing evaluation score of the present embodiment. FIG. 4A is a history of past AI singing evaluation scores, showing the number of cases for each AI singing evaluation score in a bar graph. A distribution curve based on this history (corresponding to "statistical information" according to the present invention) is indicated by a solid line. On the other hand, FIG. 4(B) is a history of standard song evaluation scores in the past, and the number of cases for each standard song evaluation score is shown in a bar graph. A distribution curve based on this history (corresponding to "statistical information" according to the present invention) is indicated by a dashed line. The distribution curve of the AI singing evaluation score in FIG. 4A and the distribution curve of the standard singing evaluation score in FIG. This embodiment shows that the AI singing evaluation score tends to be calculated lower than the standard singing evaluation score. As shown in FIGS. 4A and 4B, the distribution of AI singing evaluation scores and standard singing evaluation scores is different. It is considered that the reason is that there is no correlation between the evaluation scores of both, since it is not a scoring element for song evaluation.

In this embodiment, considering such a difference in distribution, the collected AI singing evaluation scores are corrected so as to follow the distribution curve of the standard singing evaluation scores. FIG. 4(C) is a diagram showing the distribution curve (solid line) of the AI singing evaluation score and the distribution curve (broken line) of the standard singing evaluation score. For example, when 77 points (AI singing evaluation score) are scored in the AI singing evaluation process, on the distribution curve of the AI singing evaluation score, the score on the distribution curve of the standard singing evaluation score corresponding to the position of 77 points (in this case 88 points). Thus, in the present embodiment, in the two AI song evaluation processes and the standard song evaluation process having different evaluation formats, the AI song evaluation scores gathered in the AI song evaluation process are converted into scores along the distribution of the standard song evaluation process. I am planning to correct it.

In S108, the AI singing evaluation score A calculated in the AI singing evaluation process in the form described above is corrected (first correction), and the corrected AI singing evaluation score A' is calculated. Then, the difference between the corrected AI song evaluation score A' and the standard song evaluation score B is calculated as the AI correction score T (S109). In this embodiment, the calculated AI correction score T is notified (displayed) to the user as the result of the song evaluation. By displaying the AI correction score T, the user can recognize the difference between the conventional singing evaluation (standard singing evaluation) and the new singing evaluation (AI singing evaluation).

Here, if the AI song evaluation becomes lower, it is conceivable that the user's impression of the new song evaluation method will deteriorate. Therefore, in this embodiment, if the AI correction score T is not a value greater than 0 (S110: No), the standard song evaluation score is corrected (in this case, added), and the corrected standard song evaluation score B' is calculated. (S111). By performing such a correction (second correction), the AI correction score T is a value of 0 or more, that is, the corrected AI song evaluation score A ' is a corrected standard song evaluation score B ' or more. I'm trying to be

On the other hand, if the AI correction score T is greater than 0 (S110: Yes), it is determined whether the AI correction score T is smaller than the predetermined value X (S112). This determination is made to determine whether the corrected AI singing evaluation score A' is unnecessarily larger than the standard singing evaluation score B (the difference is greater than the predetermined value X). If the AI correction score T is smaller than the predetermined value X (S112: No), the standard song evaluation score B is not corrected, and the standard song evaluation score without correction is used for the song evaluation display process (S114). On the other hand, if the AI correction score T is equal to or greater than the predetermined value X (S112: No), the standard song evaluation score B is corrected (third correction) so that the AI correction score T is equal to the predetermined value X, and corrected. Then, the standard song evaluation score B' obtained is calculated (S113). In this way, in this embodiment, the standard song evaluation score B is corrected (third correction) so that the corrected AI song evaluation score A' does not greatly exceed the standard song evaluation score B.

By correcting the AI song evaluation score A and the standard song evaluation score B calculated as described above, the AI song evaluation score A after correction is adjusted to the standard song evaluation distribution, which is a conventional song evaluation method. It is possible to correct to a value (AI singing evaluation score A′ after correction) along. In addition, by correcting the standard song evaluation score B so that the corrected AI song evaluation score A 'is a value equal to or higher than the standard song evaluation score B, the user's response to AI song evaluation, which is a new song evaluation method It is possible to make a good impression. Furthermore, when the corrected AI singing evaluation score A' greatly exceeds the standard singing evaluation score B, the standard singing evaluation score B is corrected to set the difference between the two (AI correction score T) to an appropriate value. becomes possible.

FIG. 5 is a diagram showing correction processing and various display items according to the present embodiment. The standard singing evaluation process in this embodiment calculates the element evaluation score for each of the three singing elements (pitch, rhythm, technique). The standard singing evaluation score B calculated at the end of singing is the sum of the pitch element evaluation score (20 points), the rhythm element evaluation score (20 points), and the technique element evaluation score (30 points) (70 points). becomes.

On the other hand, the AI singing evaluation score A calculated in the AI singing evaluation process is 50 points. A first correction (S108 in FIG. 3) is performed on the AI singing evaluation score A. As described above, the first correction corrects the AI singing evaluation score A on the distribution based on the AI singing evaluation score calculated in the past to follow the distribution based on the standard singing evaluation score similarly calculated in the past. It is a process to As in the example illustrated in FIG. 4, when the distribution of the AI singing evaluation score A is located on the lower score side than the distribution of the standard singing evaluation score B, a correction to increase the AI singing evaluation score A is performed. . In the case of FIG. 5, the AI singing evaluation score A (50 points) is increased by 18 points and corrected to the corrected AI singing evaluation score A' (68 points).

Next, an AI correction score T, which is the difference (A'-B) between the corrected AI song evaluation score A' (68 points) and the standard song evaluation score B (70 points), is calculated. In this case, since the AI correction score T is a negative value (-2) (S110 in FIG. 3: No), correction to the standard song evaluation score B (second correction, S111 in FIG. 3) is performed. In the example of FIG. 5, a predetermined ratio is subtracted from each element evaluation score that constitutes the standard song evaluation score B, and the corrected standard song evaluation score B' is 63 points. Therefore, the corrected standard song evaluation score B' is 68 points, and the AI corrected score T is 5 points.

In the song evaluation display process, various corrected scores are used. FIG. 6 is a song evaluation result screen when using the corrected scores described in FIG. In this embodiment, the song evaluation result screen is displayed on the monitor 41 of the karaoke device 2 after the song is finished. Note that the song evaluation result screen may be displayed on the touch panel monitor 11 of the remote control device 1 .

The song evaluation result screen is provided with song-related information 61 (song title display column 61a, singer name display column 61b), singing date and time display column 66b, and singing user name display column 67 of the sung song. In addition, an AI singing evaluation score display column 64 that displays the corrected AI singing evaluation score A', and element evaluation score display columns 62a to 62c that display the element evaluation score for each song element with respect to the corrected standard singing evaluation score B' , a standard song evaluation score display field 65 for displaying the corrected standard song evaluation score B' is provided. An AI correction score display field 63 is provided for displaying an AI correction score T, which is the difference between the corrected AI song evaluation score A' and the corrected standard song evaluation score B'.

An average score display column 68 for displaying the corrected average score of the AI singing evaluation score and a national ranking list next column 69 for displaying the national ranking of the user who sang the song are provided.

In addition, the song evaluation result screen is provided with an overall evaluation display field 70 and a vocal range display field 71 for displaying the overall evaluation and vocal range created based on the AI singing evaluation process or the standard singing evaluation process. The vocal range display field 71 displays the vocal range of the song (the lowest and highest notes required for singing) and the vocal range of the user who sang (the lowest and highest notes sung). In this way, in this embodiment, by correcting the AI song evaluation score A and the standard song evaluation score B, the corrected AI song evaluation score A' is corrected to a score along the distribution of the standard song evaluation score B. , the AI correction score T is set to a value of 0 or more to give a good impression of the new singing evaluation method.

Next, another example of correction will be described. FIG. 7 is a diagram showing correction processing and various display items of the present embodiment. In this example, the standard singing evaluation score B calculated at the end of singing is the sum of the pitch element evaluation score (23 points), the rhythm element evaluation score (22 points), and the technique element evaluation score (35 points). (80 points).

On the other hand, the AI singing evaluation score A calculated in the AI singing evaluation process is 70 points. A first correction (S108 in FIG. 3) is performed on the AI singing evaluation score A. In the example of FIG. 7, the AI singing evaluation score A (70 points) is increased by 25 points to correct the corrected AI singing evaluation score A' (95 points).

Next, an AI correction score T, which is the difference (A'-B) between the corrected AI song evaluation score A' (95 points) and the standard song evaluation score B (80 points), is calculated. In this case, since the AI correction point number T is a positive value (15) (S110 in FIG. 3: Yes), the AI correction point number T and the predetermined value X are compared (S112). In this example, the predetermined value X is 10 points, and the AI correction score T becomes a value larger than the predetermined value X (S112). Therefore, the correction (third correction, S113) for the standard song evaluation score B is executed. In the example of FIG. 7, a predetermined ratio is added to each element evaluation score that constitutes the standard song evaluation score B, and the corrected standard song evaluation score B' is corrected to 85 points. Therefore, the corrected standard song evaluation score B' is 85 points, and the AI corrected score T is 10 points (the same value as the predetermined value X).

Although the karaoke machine 2 of the present embodiment has been described above, the present invention is not limited to the above-described embodiment, and various modifications can be adopted. Modifications will be described below.

(Modification 1)
In the above-described embodiment, the correction (S108) for the AI singing evaluation score A is, as described in FIG. A distribution curve (corresponding to the "statistical information" according to the present invention) based on the history of the standard song evaluation score B is used. Various aspects can be adopted for the history of the AI singing evaluation score and the history of the standard singing evaluation score B used for this correction (first correction).

For example, (1) the history of all songs used in the karaoke machine 2 is used. (2) Use history for each karaoke song. (3) Use history of karaoke songs for each genre. (4) Use the history of karaoke songs for each singer. can be considered.

In the case of (1), the distribution curve based on the history of the AI singing evaluation score and the distribution curve based on the history of the standard singing evaluation score B are the same for the songs used in the karaoke machine 2, and the same correction is performed for all songs. will be taken. In the case of (2), the distribution curve based on the history of the AI singing evaluation score and the distribution curve based on the history of the standard singing evaluation score B are different for each song (sung song) used in the song playback process. Correction is performed according to the characteristics. In the case of (3), the distribution curve based on the history of the AI singing evaluation score and the distribution curve based on the history of the standard singing evaluation score B are different for each genre of the music used in the music playback process (sung music). Correction is performed according to the characteristics of the genre. In the case of (4), for each singer of the song used in the song playback process (sung song), the distribution curve based on the history of the AI singing evaluation score and the distribution curve based on the history of the standard singing evaluation score B are different, Correction is performed according to the characteristics of the singer.

(Modification 2)
In the embodiment described above, the first correction (S108), the second correction (S111), and the third correction (S113) are performed in the music reproduction process described with reference to FIG. These corrections are not necessarily required. For example, if there is no significant difference between the distribution of the AI singing evaluation score A and the distribution of the standard singing evaluation score B, the first correction (S108) need not be performed. Further, the second correction (S111) and the third correction (S113) are also omitted. good.

As above, the karaoke device 2 that enables the song evaluation of the present embodiment has been described, but the present invention is not limited to the karaoke device, and the remote control device 1, the smartphone possessed by the user, or the device installed in the home. A song evaluation program that is executed by various information processing devices such as personal computers and game machines and realizes the same song evaluation function as the karaoke machine 2 of the present embodiment also belongs to the scope of the present invention.

1: remote control device 31: video control unit 2: karaoke device 32: hard disk 5: server device 33: touch panel monitor 11: touch panel monitor 34: touch panel 11a: display unit 35: display unit 11b: touch panel 41: monitor 12: video RAM 42 : Speaker 13: Video control unit 43a, 43b: Microphone 14: Memory 61: Music related information 15: CPU 61a: Music name display field 16: Wireless LAN communication part 61b: Singer name display field 17: Operation part 62a to 62c: Elements Evaluation score display column 18: Operation processing unit 63: AI correction score display column 21: Operation unit 64: AI singing evaluation score display column 22: Operation processing unit 65: Standard song evaluation score display column 24a: LAN communication unit 66b: Singing date and time Display column 24b: Wireless LAN communication unit 67: Singing user name display column 25: Sound control unit 68: Average score display column 27: Memory 69: National ranking table next column 28: Video RAM 70: Overall evaluation display column 29: Video playback unit 71: vocal range display field 30: CPU 130: access point

Claims (8)

A karaoke device that performs singing evaluation based on a singing voice signal input from a microphone,
making it possible to execute a first evaluation process, a second evaluation process, and a notification process;
The first evaluation process evaluates the singing voice signal input from the microphone by a first evaluation method, calculates a first singing evaluation value,
The second evaluation process evaluates the singing voice signal input from the microphone by a second evaluation system different from the first evaluation system, and a second song evaluation having the same scale as the first evaluation process. Calculate the value of
The notification process notifies the first song evaluation value for the one singing voice signal and the difference value between the first song evaluation value and the second song evaluation value for the one singing voice signal. Karaoke apparatus. The karaoke apparatus according to claim 1, wherein at least one of the first evaluation process and the second evaluation process calculates the first evaluation value or the second evaluation value after performing a correction process. 3. The correction process in the first evaluation process calculates the first evaluation value based on a correction value based on the statistical information of the first song evaluation value and the statistical information of the second song evaluation value. karaoke device. The karaoke machine according to any one of claims 1 to 3, wherein the first evaluation method used in the first evaluation process is an evaluation method using AI. The second evaluation method used in the second evaluation process divides the same scale as that used in the first evaluation process into a plurality of scales for each of the plurality of singing elements, and sings with each scale for each of the plurality of singing elements. The karaoke machine according to any one of claims 1 to 4, which is an evaluation method for calculating an evaluation value. The karaoke device according to claim 5, wherein the second evaluation process performs correction for each of the singing elements. The karaoke device according to claim 5 or 6, wherein the notification process notifies the first song evaluation value in association with the song evaluation value for each of the plurality of song elements of the second evaluation process . A song evaluation program executable by an information processing device,
making it possible to execute a first evaluation process, a second evaluation process, and a notification process;
The first evaluation process evaluates a singing voice signal input from a microphone by a first evaluation method, calculates a first singing evaluation value,
The second evaluation process evaluates the singing voice signal input from the microphone by a second evaluation method different from the first evaluation method, calculates a second singing evaluation value,
The song evaluation program, wherein the notification process notifies the first song evaluation value and a difference value between the first song evaluation value and the second song evaluation value.

Images