JP6954780B2 - Karaoke equipment - Google Patents

Description

The present invention relates to a karaoke device.

The karaoke device can score karaoke singing by comparing the singing voice data extracted from the singing voice input by the microphone with the reference data indicating the main melody of the music played in karaoke.

For example, in Patent Document 1, pitch data and pitch data are extracted from a singing voice signal input from a microphone in accordance with a karaoke performance, and compared with a guide melody read in parallel with the karaoke performance. A technique for scoring and evaluating skill is disclosed.

On the other hand, since there is a difference in the singing skills of the singers, even if they sing hard, if the deviation from the reference data is large, it is not possible to obtain a sufficient scoring evaluation. Therefore, Patent Document 2 discloses a technique for extracting an emotional feature amount that correlates with how to put emotions from a voice corresponding to singing and analyzing the emotions put into the singing based on the emotional feature amount. There is. According to such a technique, the emotional expression of the singer can be evaluated.

Japanese Unexamined Patent Publication No. 10-6916 Japanese Unexamined Patent Publication No. 10-187178

By the way, in karaoke music (each singing section included in the karaoke music), various atmospheres such as a fun atmosphere and a sad atmosphere are expressed by lyrics and tunes. Therefore, it can be said that singing with emotional expression considering the atmosphere of each karaoke song is a skillful karaoke singing.

Here, in the technique disclosed in Patent Document 2, regardless of the atmosphere of the karaoke music, if the song is sung hard (for example, if the volume and the degree of enthusiasm are high), the evaluation will be high. That is, the technique disclosed in Patent Document 2 cannot evaluate the emotional expression in consideration of the atmosphere of the karaoke music.

An object of the present invention is to provide a karaoke device capable of appropriately evaluating whether or not singing is performed with an emotional expression suitable for the atmosphere of a karaoke music.

The main invention for achieving the above object is an emotion reference data acquisition unit that acquires emotion reference data indicating emotions to be expressed when singing a karaoke song for each singing section, and an emotion reference data acquisition unit obtained by singing the karaoke song. By comparing the emotion reference data and the singing emotion data with the singing emotion data generation unit that generates the singing emotion data obtained by emotionally analyzing the singing voice, the emotion expression of each singing section can be expressed. It is a karaoke device having an emotion expression evaluation unit for evaluation.
Other features of the present invention will be clarified by the description of the description and drawings described later.

According to the present invention, it is possible to appropriately evaluate whether or not the singing is performed with an emotional expression suitable for the atmosphere of the karaoke music.

It is a figure which shows the hardware configuration example of the karaoke apparatus which concerns on embodiment. It is a figure which shows the software configuration example of the apparatus main body which concerns on embodiment. It is a figure which shows the example of data stored in the word-emotion type database which concerns on embodiment. It is a figure which shows the example of data stored in the music tone-emotion type database which concerns on embodiment. It is a figure which showed the lyrics and the music tone for each singing section included in the karaoke music which concerns on embodiment. It is a figure which showed the total score for each singing section included in the karaoke music which concerns on embodiment. It is a figure which showed the emotion reference data which concerns on embodiment. It is a figure which showed the singing emotion data which concerns on embodiment. It is a figure which showed the evaluation of the emotional expression which concerns on embodiment. It is a flowchart which shows the process of the karaoke apparatus which concerns on embodiment. It is a figure which shows the software configuration example of the apparatus main body which concerns on the modification. It is a figure which showed the emotion reference data which concerns on a modification.

<Embodiment>
The karaoke device 1 according to the present embodiment will be described with reference to FIGS. 1 to 9.

== Karaoke device ==
The karaoke device 1 is a device for performing karaoke performance of a song selected by a singer and singing karaoke by the singer. As shown in FIG. 1, the karaoke device 1 includes a karaoke body 10, a speaker 20, a display device 30, a microphone 40, and a remote control device 50.

The speaker 20 is configured to emit sound based on the sound emitted signal from the karaoke main body 10. The display device 30 is configured to display an image or an image on the screen based on the signal from the karaoke main body 10. The microphone 40 is configured to convert the singing voice of the singer (input voice from the microphone 40) into an analog singing voice signal and input it to the karaoke main body 10.

(Karaoke hardware)
As shown in FIG. 1, the karaoke main body 10 includes a control unit 11, a communication unit 12, a storage unit 13, an acoustic processing unit 14, a display processing unit 15, and an operation unit 16. Each configuration is connected to bus B via an interface (not shown).

The karaoke body 10 performs various controls related to karaoke singing, such as karaoke performance control of selected songs, display control of lyrics and background images, and processing of singing voice signals input through a microphone 40.

The control unit 11 includes a CPU 11a and a memory 11b. The CPU 11a realizes various control functions by executing an operation program stored in the memory 11b. The memory 11b is a storage device that stores a program to be executed in the CPU 11a and temporarily stores various information when the program is executed.

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

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

Identification information (music ID) for identifying each karaoke music is added to the music data. The music data includes accompaniment data, reference data, background image data, lyrics data, and attribute information. The accompaniment data is MIDI format data that is the source of the karaoke performance sound. Reference data is data used as a reference when scoring karaoke singing by a singer. The reference data includes pitch (pitch) data, sound length data, timing data, and the like. The background image data is data corresponding to the background image displayed on the display device 30 or the like at the time of karaoke performance. The lyrics data is data related to lyrics (lyric telop) to be displayed on the display device 30 or the like. The attribute information is information about the music such as a song name, a singer name, a lyricist / composer name, and a genre.

Based on the control of the control unit 11, the sound processing unit 14 controls the performance of the karaoke music and processes the singing voice signal input through the microphone 40. The sound processing unit 14 includes, for example, a MIDI sound source, a mixer, and an amplifier (none of which are shown). The control unit 11 sequentially reads out the accompaniment data of the reserved music based on the tempo clock signal and inputs it to the MIDI sound source. The MIDI sound source generates a musical tone signal based on the accompaniment data. The mixer mixes the music signal and the singing audio signal output from the microphone 40 at an appropriate ratio and outputs the sound signal to the amplifier. The amplifier amplifies the mixing signal from the mixer and outputs it to the speaker 20 as a sound emission signal. As a result, the karaoke performance sound based on the sound emission signal and the singing sound from the microphone 40 are emitted from the speaker 20.

The display processing unit 15 performs processing related to various displays in the display device 30 based on 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 lyrics and various icons are superimposed on a background image during a karaoke performance.

The operation unit 16 includes a panel switch, a remote control reception circuit, and the like, and sends operation signals such as a music selection signal and a performance stop signal to the control unit 11 in response 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 the operation signal from the operation unit 16 and executes the corresponding process.

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 karaoke song that he / she wishes to sing.

(Karaoke main unit software)
FIG. 2 is a diagram showing a software configuration example of the karaoke main body 10. The karaoke body 10 includes a word-emotion type database 100, a song tone-emotion type database 200, an emotion reference data acquisition unit 300, a singing emotion data generation unit 400, an emotion expression evaluation unit 500, a scoring processing unit 600, and a karaoke singing evaluation unit 700. To be equipped. The word-emotion type database 100 and the tune-emotion type database 200 are provided as part of the storage area of the storage unit 13. The emotion reference data acquisition unit 300, the singing emotion data generation unit 400, the emotion expression evaluation unit 500, the scoring processing unit 600, and the karaoke singing evaluation unit 700 are realized by the CPU 11a executing a program stored in the memory 11b. ..

[Word-Emotion type database]
The word-emotion type database 100 associates emotion types with each of the words contained in the lyrics of various karaoke songs. Emotion types correspond to general emotional expressions such as emotions. FIG. 3 shows a part of the data stored in the word-emotion type database 100. In this example, three emotion types are set: "joy", "anger", and "sadness". Each word is given a predetermined score (5 grades of 1 to 5 points in this example) for each emotion type. For example, for the word "not", a score of "joy: 1 point, anger: 3 points, sadness: 5 points" is given for each emotion type.

[Song-Emotion Type Database]
The music tone-emotion type database 200 associates the music tone used for the karaoke music with the emotion type. FIG. 4 shows a part of the data stored in the tune-emotion type database 200. In this example, as in FIG. 3, three types of emotions, "joy", "anger", and "sadness", are set. In the example of FIG. 4, the musical tone is classified by a plurality of chords. Each code is given a predetermined score (5 grades of 1 to 5 points in this example) for each emotion type. For example, for the major code, a score of "joy: 5 points, anger: 1 point, sadness: 1 point" is given for each emotion type. Further, "major" is a major chord (chord in major) such as C, E, F, G, and "minor" is a minor chord (chord in minor) such as Dm, Em, Am. ..

It is sufficient that at least one emotion type is associated with one word or one tune. For example, it is possible to associate only one most dominant emotion type with a word (a certain tune), or conversely, associate four or more emotion types. It is also possible that words that are not registered in the word-emotion type database 100 are used in the lyrics. Therefore, the word-emotion type database 100 may store a score such as "joy: 1 point, anger: 1 point, sadness: 1 point" as "other".

[Emotion reference data acquisition department]
The emotion reference data acquisition unit 300 acquires emotion reference data indicating emotions to be expressed when singing a karaoke song for each singing section.

Each singing section of a karaoke song has an atmosphere suitable for singing. That is, when singing a karaoke song, there are appropriate emotions to be expressed for each singing section. For example, for a karaoke song with a sad atmosphere, it is appropriate to express the feeling of sadness. The emotional reference data is data to be referred to when determining whether or not such emotional expression is properly performed. The acquisition of emotional reference data is performed based on at least one of the lyrics and the tone of the karaoke song.

FIG. 5 shows the lyrics and tunes for each singing section included in the karaoke song X. Each lyrics is composed of multiple words. The emotion reference data acquisition unit 300 acquires emotion reference data for each singing section shown in FIG.

For example, the lyrics of singing section A include two words, "you" and "not". The code of the singing section A is "Am" (see FIG. 5).

In this case, the emotion reference data acquisition unit 300 reads out the score for each emotion type for each of the word "you" and the word "not" from the word-emotion type database 100. Referring to the example of FIG. 3, the word "you" has a score of "joy: 5 points, anger: 3 points, sadness: 5 points", and the word "not" has "joy: 1 point, anger: 3 points". , Sadness: 5 points ”.

The emotion reference data acquisition unit 300 adds the scores read out for the lyrics (two words) in the singing section A for each emotion type. In the example of the singing section A, "joy: 6 points, anger: 6 points, sadness: 10 points".

Further, the emotion reference data acquisition unit 300 reads out the score for each emotion type for the code "Am" from the song tone-emotion type database 200. Referring to the example of FIG. 4, since the code "Am" is a minor, the score is "joy: 1 point, anger: 3 points, sadness: 5 points".

The emotion reference data acquisition unit 300 has a score based on the lyrics of the singing section A (joy: 6 points, anger: 6 points, sadness: 10 points) and a score based on the tune of the singing section A (joy: 1 point, anger: anger:). The total score (joy: 7 points, anger: 9 points, sadness: 15 points) is calculated by adding 3 points, sadness: 5 points) for each emotion type. In the present embodiment, the score based on the lyrics consisting of a plurality of words included in one singing section and the score based on one tune are simply added, but depending on the length of the singing section, the number of words and the number of tunes, and the like. Then, they may be weighted and added.

The emotion reference data acquisition unit 300 similarly obtains the total score for each emotion type for the remaining singing sections B to H (see FIG. 6A). Then, the emotion reference data acquisition unit 300 acquires the emotion reference data by calculating the ratio of the total score added for each emotion type for each singing section (see FIG. 6B). In this way, the emotion reference data can be acquired as a numerical value for each emotion type.

In the present embodiment, an example of acquiring emotion reference data based on lyrics (words) and tunes has been described, but emotion reference data may be acquired based on only one of them (for example, only words). .. Also, the emotion reference data does not have to be a numerical value based on the emotion type ratio. For example, in the emotion reference data, the emotion type with the highest score may be set to 100 points for a certain singing section, and the other emotion types may be set to 0 points. In the example of the singing section A of FIG. 6B, the highest score "sadness" may be set to 100 points, and "joy" and "anger" may be set to 0 points. Further, in the present embodiment, the example in which one chord (tune) is included in one singing section has been described, but there may be a case where a plurality of chords are included in one singing section. In that case, the emotion reference data acquisition unit 300 may acquire the sum of the scores of the plurality of codes for each emotion type as the score of one singing section.

[Singing emotion data generation unit]
The singing emotion data generation unit 400 generates singing emotion data for each singing section, which is an emotion analysis of the singing voice obtained by singing the karaoke song.

The singing emotion data is data showing the emotional expression included in the actual karaoke singing. In this embodiment, the singing emotion data is shown numerically. Singing emotion data is obtained by emotionally analyzing the singing voice. For emotion analysis, known techniques (for example, Patent Document 2 and "Voice Heart Analysis Service" (Hitachi Systems, Ltd.)) can be used. As a specific example, the singing emotion data generation unit 400 extracts an emotional feature amount that correlates with how to put emotions from the singing voice. In addition, the singing emotion data generation unit 400 analyzes the emotions contained in the singing based on the extracted emotional features. Sentiment analysis is performed for each predetermined singing section. Then, the singing emotion data generation unit 400 generates singing emotion data for each singing section by quantifying the information obtained by the emotion analysis and classifying it into a predetermined emotion type.

Alternatively, it is also possible to generate singing emotion data using a known artificial intelligence technique. For example, the PC development support kit "ST Emotion SDK" (AGI Co., Ltd.) has a function to detect emotional states such as joy, anger, and sorrow and the intensity of excitement in 10 stages from conversational voice using the voice emotion recognition engine ST. Exists. The singing emotion data generation unit 400 has a function similar to that of such a kit, and it is possible to detect the emotion of the singer by machine learning the emotion analysis of the singing voice. In this case, the singing emotion data generation unit 400 can generate singing emotion data for each singing section by quantifying the detected information and classifying it into a predetermined emotion type.

FIG. 7 shows singing emotion data when the singer sings the lyrics of the karaoke song X shown in FIG. In this example, singing emotion data is generated by classifying the emotion analysis results into three emotion types for each singing section. Further, in the example of FIG. 7, the total score of the three emotion types is adjusted to be 100 points or less. In the singing emotion data, the emotion type having the highest score may be set to 100 points for a certain singing section, and the other emotion types may be set to 0 points. Further, at least one emotion type may be associated with one singing section. For example, it is possible to associate only one of the most dominant emotion types with a singing section, or conversely, associate four or more emotion types.

[Emotional expression evaluation department]
The emotional expression evaluation unit 500 evaluates the emotional expression for each singing section by comparing the emotional reference data with the singing emotional data.

Emotional expression is evaluated by quantifying how much emotion is contained in karaoke singing. Specifically, the emotion expression evaluation unit 500 compares the emotion reference data and the singing emotion data for each emotion type, and evaluates the emotion expression by the total value of the scores obtained for each emotion type. In this case, the emotion reference data and the singing emotion data are preferably composed of a plurality of common emotion types.

For example, suppose that the emotion reference data acquisition unit 300 acquires the emotion reference data shown in FIG. 6B, and the singing emotion data generation unit 400 generates the singing emotion data shown in FIG. 7.

In this case, the emotion expression evaluation unit 500 takes an AND of the score of the emotion reference data and the score of the singing emotion data for each emotion type in the singing section A. Specifically, "joy: 23 points & 10 points = 10 points", "anger: 29 points & 0 points = 0 points", and "sadness: 48 points & 20 points = 20 points". Then, the emotion expression evaluation unit 500 evaluates the singing section A by the total value (10 points + 20 points = 30 points) of the scores of each emotion type. The emotional expression evaluation unit 500 performs the same processing for the singing sections B to H, and evaluates the emotional expression for each singing section (see FIG. 8). Since the score of the emotion reference data in a certain singing section is 100 points and the maximum value of the score of the singing emotion data in a certain singing section is 100 points, the evaluation for each singing section is 100 points.

The emotional expression evaluation unit 500 can present the evaluation result to the singer. For example, the emotional expression evaluation unit 500 can display the evaluation result shown in FIG. 8 on the display device 30. Alternatively, the emotional expression evaluation unit 500 can calculate the average value of the scores for each singing section (53.125 points in the example of FIG. 8) and present the average value.

When the emotion type with the highest score is set to 100 points in the emotion reference data, the other points are set to 0 points, and the emotion type other than the emotion type having the highest score in the singing emotion data is set to 0 points, the emotion expression evaluation unit 500 will use the emotion expression evaluation unit 500. In essence, the evaluation is made from the viewpoint of whether or not the dominant emotion types match for each singing section.

[Scoring section]
The scoring processing unit 600 calculates the scoring value by scoring the singing voice data extracted from the singing voice based on at least one of pitch, volume and singing technique.

Known techniques can be used for scoring karaoke songs. For example, the scoring processing unit 600 extracts singing voice data such as pitch (pitch) data and volume data from the singing voice signal input from the microphone 40, and compares it with the reference data of the karaoke music to score the scoring value. Is calculated.

[Karaoke Singing Evaluation Department]
The karaoke singing evaluation unit 700 evaluates the singing of the karaoke music based on the evaluation of the emotional expression based on the singing of the karaoke music and the scoring value.

The evaluation of the karaoke singing in the present embodiment is performed by comprehensively evaluating whether the karaoke singing is performed according to the reference data and whether the appropriate emotional expression is performed.

For example, it is assumed that the average value of the emotional expression evaluation of each singing section by the emotional expression evaluation unit 500 of the entire karaoke song X is 60 points, and the scoring result by the scoring processing unit 600 is 85 points.

In this case, the karaoke singing evaluation unit 700 uses these scores to evaluate the singing of the karaoke song X. For example, when the weighting of "scoring result: evaluation of emotional expression = 9: 1" is set, the karaoke singing evaluation unit 700 has (85 points x 0.9) + (60 points x 0.1) = 82. .5 points are calculated as the score of the singing evaluation of the karaoke song X.

Alternatively, when the evaluation of emotional expression is added as a bonus point of 10% to the scoring result, the karaoke singing evaluation unit 700 adds 85 points + (60 points x 0.1) = 91 points to the singing evaluation score of the karaoke song X. Calculate as. When the addition method is adopted in this way, the upper limit is preferably the maximum value (for example, 100 points) provided in the scoring function of the karaoke device 1.

The karaoke singing evaluation unit 700 can present the evaluation result to the singer. For example, the karaoke singing evaluation unit 700 can display the calculated score on the display device 30.

== About the operation of the karaoke device 1 ==
Next, a specific example of the operation of the karaoke device 1 in the present embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an operation example of the karaoke device 1.

The karaoke device 1 performs a karaoke performance based on the accompaniment data of the karaoke music X selected by the singer (Karaoke performance, step 10). The singer sings karaoke along with the karaoke performance.

After the karaoke singing of the karaoke song X is completed, the emotion reference data acquisition unit 300 acquires the emotion reference data indicating the emotion to be expressed when singing the karaoke song X for each singing section (acquisition of the emotion reference data). Step 11).

The singing emotion data generation unit 400 analyzes the singing voice obtained by singing the karaoke song X, and generates singing emotion data for each singing section (generation of singing emotion data, step 12).

The emotional expression evaluation unit 500 evaluates the emotional expression for each singing section by comparing the emotional reference data acquired in step 11 with the singing emotional data generated in step 12 (evaluation of emotional expression. Step 13). ).

The scoring processing unit 600 calculates the scoring value by comparing the singing voice data extracted from the singing voice obtained by singing the karaoke music X with the reference data (calculation of the scoring value, step 14).

The karaoke singing evaluation unit 700 evaluates the karaoke song X based on the evaluation of the emotional expression performed in step 13 and the scoring value calculated in step 14 (evaluation of karaoke singing, step 15).

In the above example, the example of processing after the karaoke singing of the karaoke song X is completed has been described, but the evaluation of the emotional expression may be performed after the karaoke singing of at least one singing section is completed. For example, the processing of steps 11 to 14 is performed after the singing of the singing section A is completed, the processing of steps 11 to 14 is performed after the singing of the singing section B is completed, the processing of steps 11 to 14 is performed after the singing of the singing section C is completed, and so on. , The processing of steps 11 to 14 may be repeated until the end of the karaoke song X, and finally the singing evaluation of the karaoke song X may be performed based on the evaluation of the emotional expression and the scoring value in each singing section.

Further, the emotion reference data may be stored in the storage unit 13 as the emotion reference data generated based on the lyrics and the tone of the karaoke music. In this case, the emotion reference data acquisition unit 300 directly acquires the emotion reference data from the storage unit 13.

As described above, the karaoke device 1 according to the present embodiment sings the karaoke song together with the emotion reference data acquisition unit 300 that acquires the emotion reference data indicating the emotion to be expressed when singing the karaoke song for each singing section. Evaluation of emotional expression for each singing section by comparing the singing emotion data generation unit 400, which generates singing emotion data obtained by emotionally analyzing the singing voice obtained in the above, for each singing section, and the emotion reference data and the singing emotion data. It has an emotional expression evaluation unit 500 that performs the above.

By comparing the singing emotion data obtained by emotionally analyzing the singing voice with the emotion reference data, the evaluation is high when the emotion expression considering the atmosphere of the karaoke song is made. On the other hand, singing that does not consider the atmosphere, such as when singing in a loud voice, has a low evaluation. That is, according to the karaoke device 1 according to the present embodiment, it is possible to appropriately evaluate whether or not the singing is performed with an emotional expression suitable for the atmosphere of the karaoke music.

Further, in the karaoke device 1 according to the present embodiment, the emotion reference data and the singing emotion data are composed of a plurality of common emotion types, and the emotion expression evaluation unit 500 includes emotion reference data and singing emotion data for each emotion type. Make a comparison. In this way, by comparing the emotion reference data and the singing emotion data for each of the plurality of emotion types, it is possible to more accurately determine whether or not the emotion expression suitable for the atmosphere of the karaoke song is made.

Further, the karaoke device 1 according to the present embodiment includes a scoring processing unit 600 that calculates a scoring value by scoring the singing voice data extracted from the singing voice based on at least one of pitch, volume and singing technique. It also has a karaoke singing evaluation unit 700 that evaluates the singing of karaoke songs based on the evaluation of emotional expressions based on the singing of karaoke songs and the scoring value. According to such a karaoke device 1, it is possible to perform a comprehensive evaluation of karaoke singing including an evaluation of emotional expression.

Further, the emotion reference data acquisition unit 300 acquires emotion reference data based on at least one of the lyrics and the tone of the karaoke song. In this way, by using at least one of the lyrics and the tone of the karaoke music, it is possible to acquire the emotion reference data that reflects the atmosphere of the karaoke music.

<Modification example>
In the above embodiment, an example in which the emotion reference data acquisition unit 300 acquires emotion reference data based on the lyrics and tone of the karaoke song has been described.

FIG. 10 is a diagram showing a software configuration example of the karaoke main body 10 according to this modification. The karaoke body 10 includes an emotion reference data acquisition unit 300, a singing emotion data generation unit 400, an emotion expression evaluation unit 500, a scoring processing unit 600, a karaoke singing evaluation unit 700, and an emotion reference data storage unit 800. The emotion reference data storage unit 800 is provided as a part of the storage area of the storage unit 13.

[Emotion reference data storage]
The emotion reference data storage unit 800 stores emotion reference data based on the singing emotion data obtained by emotionally analyzing the singing voice of the original song singer of the karaoke song. The original song singer is a professional singer who sings a karaoke song, and is a person who can sing the karaoke song best. That is, the emotional expression in each singing section can be accurately reproduced.

The emotion reference data is stored, for example, each time a new karaoke song is delivered. Specifically, the singing emotion data generation unit 400 performs singing analysis of the original singer of the new karaoke song, and generates singing emotion data composed of a plurality of emotion types. The singing emotion data generation unit 400 normalizes the ratio of a plurality of emotion types on a scale of 100 points based on the singing emotion data, and stores it as emotion reference data. FIG. 11 is a diagram showing an example of emotional reference data of the singing sections A to H in the above embodiment. As is clear from FIG. 11, the total score of the emotion type is set to a maximum of 100 points in each singing section.

[Emotion reference data acquisition department]
The emotion reference data acquisition unit 300 according to this modification acquires emotion reference data indicating emotions to be expressed when singing a karaoke song for each singing section.

The emotion reference data acquisition unit 300 acquires emotion reference data from the emotion reference data storage unit 800. For example, when the karaoke music X is selected, the emotion reference data acquisition unit 300 reads the emotion reference data of the karaoke music X from the emotion reference data storage unit 800.

As described above, according to the karaoke device 1 according to the present modification, it is not necessary to calculate the emotion reference data each time the emotion expression is evaluated. In addition, by creating emotion reference data from the singing voice of the original song singer, it is possible to evaluate an appropriate emotional expression along with the singing of the original song singer.

<Others>
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 combinations, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The above-described embodiments and modifications thereof are included in the scope and gist of the invention, as well as in the scope of the invention described in the claims and the equivalent scope thereof.

1 Karaoke device 100 Word-Emotion type database 200 Song tone-Emotion type database 300 Emotion reference data acquisition unit 400 Singing emotion data generation unit 500 Emotion expression evaluation unit 600 Scoring processing unit 700 Karaoke singing evaluation unit

Claims (4)

An emotion reference data acquisition unit that acquires emotion reference data indicating emotions to be expressed when singing a karaoke song for each singing section, and an emotion reference data acquisition unit.
A singing emotion data generation unit that generates singing emotion data obtained by emotionally analyzing the singing voice obtained by singing the karaoke song for each singing section.
An emotional expression evaluation unit that evaluates the emotional expression for each singing section by comparing the emotional reference data with the singing emotional data.
Have a,
The emotion reference data indicates emotions corresponding to the types of singing emotion data that can be generated by the singing emotion data generation unit.
The emotion reference data and the singing emotion data are composed of a plurality of common emotion types.
The emotion expression evaluation unit is a karaoke device that compares the emotion reference data with the singing emotion data for each emotion type. A scoring processing unit that calculates a scoring value by scoring singing voice data extracted from the singing voice based on at least one of pitch, volume, and singing technique.
A karaoke singing evaluation unit that evaluates the emotional expression based on the singing of the karaoke song and evaluates the singing of the karaoke song based on the scoring value.
Claim 1 Symbol placement karaoke apparatus characterized by having a. The karaoke device according to claim 1 or 2, wherein the emotion reference data acquisition unit acquires the emotion reference data based on at least one of the lyrics and the tone of the karaoke song. It has an emotion reference data storage unit that stores emotion reference data based on singing emotion data obtained by emotionally analyzing the singing voice of the original singer of the karaoke song.
The karaoke device according to claim 1 or 2, wherein the emotion reference data acquisition unit acquires the emotion reference data from the emotion reference data storage unit.

Images