Karaoke equipment

Abstract

To reflect content of narration told by a singer himself / herself in a singing evaluation of the singer.SOLUTION: A karaoke device (10) includes: determination means (22) that determines whether or not a narration voice has been input in accordance with a voice input within a prescribed time before music is performed; identifying means (23) that, in a case where a narration voice is input, identifies words from the narration voice by voice recognition processing; narration evaluation means (24) that evaluates the narration voice based on a result of comparison between the words identified by the identifying means and prescribed words; performing means (25) that starts performance of music by sensing the termination of the narration voice; singing evaluation means (26) that evaluates a singing voice based on a result of comparison between a pitch of the singing voice and a pitch of a note included in reference data of the music; and display means (27) that displays a comprehensive evaluation based on an evaluation of the narration voice and an evaluation of the singing voice.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a karaoke device. [Background technology]

[0002] When using a karaoke device, a narration by a host is inserted before the reserved song is sung, creating a sense of realism like a singing show and increasing the singer's motivation to sing. For this reason, karaoke devices that automatically insert narration before the reserved song is played have been proposed (see, for example, Patent Document 1). The karaoke device described in Patent Document 1 stores audio data of narration according to the performance content. Before the performance begins, the singing content is analyzed from attribute information such as the genre assigned to the reserved song, and the most suitable narration for the reserved song is selected and played. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 11-167388 Summary of the Invention [Problem to be solved by the invention]

[0004] By the way, before singing, singers themselves may narrate the song to explain it. Depending on the skill of this narration, it can create a sense of realism like a live performance, and the melody and lyrics information can be conveyed to the other attendees in advance, creating a lively atmosphere. For this reason, it is desirable to evaluate not only the singing ability but also the singer's narration skills.

[0005] An object of the present invention is to provide a karaoke apparatus capable of reflecting the contents of a narration spoken by a singer in an evaluation of the singer's singing. [Means for solving the problem]

[0006] The main invention for achieving the above object includes a determination means for determining whether a narration voice has been input in response to a voice input within a predetermined time before a musical piece is played, a determination means for determining words from the narration voice by a voice recognition process when the narration voice has been input, and a determination means for determining words from the narration voice by a voice recognition process when the narration voice has been input. from the number of predetermined words in the lyrics data of the music that match the word specified by the specifying means and / or the number of predetermined words expressing the melody of the music that matches the word specified by the specifying means. The karaoke device includes a narration evaluation means for evaluating a narration voice, a performance means for starting the performance of a song by detecting the end of the narration voice, a singing evaluation means for evaluating the singing voice based on a comparison result between the pitch of the singing voice and the pitch of notes included in reference data of the song, and a display means for displaying an overall evaluation based on the evaluation of the narration voice and the evaluation of the singing voice. Effect of the Invention

[0007] According to the present invention, when a voice is input before a musical piece is played, it is determined that the voice is a narration voice input by a singer, and the contents of the narration voice are evaluated based on words identified from the narration voice and predetermined words. The singing voice is also evaluated based on the pitch of the singer's singing voice and the pitch of the notes of the musical piece. Then, a comprehensive evaluation is obtained from the evaluation of the narration voice and the evaluation of the singing voice. Thus, karaoke singing can be comprehensively evaluated taking into consideration not only the singing ability of the singer but also the contents of the narration spoken by the singer. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram of a karaoke device according to a first embodiment. [Diagram 2] FIG. 1 is a functional block diagram of a karaoke device according to a first embodiment. [Diagram 3] FIG. 4 is a flow chart showing an example of a processing operation of the karaoke apparatus according to the first embodiment. [Figure 4] FIG. 11 is a functional block diagram of a karaoke device according to a third embodiment. [Diagram 5] 11A and 11B are diagrams showing an example of a narration history, an appropriate time table, and an evaluation table. [Figure 6]FIG. 11 is a flowchart showing an example of a processing operation of the karaoke apparatus according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] First Embodiment A karaoke device of a first embodiment will be described with reference to Figures 1 and 2. Figure 1 is a configuration diagram of the karaoke device of the first embodiment. Figure 2 is a functional block diagram of the karaoke device of the first embodiment. Note that, for the sake of convenience, the functional block diagram of Figure 2 shows functional blocks for realizing specific processing, but it is assumed that the device has the same configuration as a karaoke device normally has.

[0010] As shown in Fig. 1, the karaoke device 10 is provided with a device main body 11, a monitor 12, a speaker 13, a microphone 14, and a remote control device 15. The monitor 12 displays lyrics and subtitles along with a background image based on a video signal and the like from the device main body 11. The microphone 14 converts a singing voice into a singing voice signal and inputs it to the device main body 11. The speaker 13 emits a singing voice along with a performance sound based on a performance sound signal from the device main body 11 and a singing voice signal from the microphone 14. The remote control device 15 accepts various operations by a user on the device main body 11, such as reserving songs.

[0011] When the device main body 11 starts the karaoke performance, lyrics captions and background images are displayed on the monitor 12 in sync with the karaoke performance. In the device main body 11, the karaoke performance sound signal and the singing voice signal input from the microphone 14 are mixed by the mixer, and this mixed signal is amplified by the amplifier and output from the speaker 13. In this way, when a singer sings along with the karaoke performance, the singing voice is output from the speaker 13 together with the performance sound. In addition, the device main body 11 evaluates the singer's singing ability, etc., and the evaluation result of the singer is displayed on the monitor 12.

[0012] As shown in Fig. 2, the device main body 11 is configured to evaluate not only the singing ability of a singer, but also the narration skill of the singer himself / herself. The device main body 11 is provided with a storage means 21, a judgment means 22, a specification means 23, a narration evaluation means 24, a performance means 25, a singing evaluation means 26, and a display means 27. The storage means 21 stores various data related to karaoke singing, such as music data for each music ID. The music data includes performance data that is the basis of the performance sound, reference data that is the evaluation standard for the singing voice, and lyric data that is the basis of the lyric telop and is the evaluation standard for the narration voice.

[0013] The determination means 22 determines whether or not a narration voice has been input in response to a voice input within a predetermined time before the performance of a piece of music. Specifically, the performance of the next reserved piece of music is put on hold until a predetermined time (e.g., 10 seconds) has elapsed since the performance means 25 finished playing the piece of music. If a voice signal is input from the microphone 14 to the determination means 22 within this predetermined waiting time, the determination means 22 determines that a narration voice has been input. If a predetermined time has elapsed without a voice signal being input from the microphone 14 to the determination means 22, the determination means 22 determines that a narration voice has not been input.

[0014] When a narration voice is input, the identification means 23 identifies words from the narration voice by voice recognition processing. Specifically, from the point in time when it is determined that a narration voice is input, the voice signal output from the microphone 14 is subjected to voice recognition processing to convert the voice signal into text. This generates text data according to the singer's narration voice, and the text data is broken down into parts of speech by natural language analysis (morphological analysis) to identify words such as "lovely" and "sad." Note that publicly known technologies can be used for the voice recognition processing and natural language analysis.

[0015] The narration evaluation means 24 evaluates the narration voice based on the comparison result between the words identified by the identification means 23 and predetermined words included in the lyrics data of the music piece. Specifically, the narration evaluation means 24 reads the lyrics data in the music piece data from the storage means 21, and compares the words identified from the narration voice with predetermined words in the lyrics data. If the lyrics data contains words such as "lovely" or "sad," the number of words included in the lyrics data is counted to evaluate the narration voice. For example, if the number of words is 12, 12 points are calculated as the evaluation of the narration voice.

[0016] The performance means 25 detects the end of the narration voice and starts playing the next reserved song waiting to be played. Specifically, the performance means 25 detects the end of the narration voice when a command to start playing is input from the karaoke device 10 or the remote control device 15, or when a specific phrase such as "Now, please listen" is input by voice. Then, the performance means 25 reads out the performance data in the song data from the storage means 21 and plays it. Note that, if the determination means 22 determines that no narration voice has been input, the performance of the next reserved song waiting to be played is automatically started.

[0017] The singing evaluation means 26 evaluates the singing voice based on the comparison result between the pitch of the singing voice and the pitch of the note included in the reference data of the song. Specifically, the singing evaluation means 26 reads out the reference data in the song data from the storage means 21, and the singing voice signal of the singer is input to the singing evaluation means 26 from the microphone 14. During the note-on period of each note in the reference data, the pitch of the singing voice is compared with the pitch of the note, and depending on the degree of agreement between the pitch of the singing voice and the pitch of the note, the singing voice for that note is judged as pass / fail, and a singing evaluation showing the pitch accuracy is performed.

[0018] More specifically, as described in JP 2005-049410 A, the singing frequency and the reference frequency are compared at each sample timing (e.g., every 20 milliseconds), and the difference (cent value) between the singing frequency and the reference frequency is calculated. A note whose difference falls within an allowable range (e.g., within ±50 cents) a predetermined number of times or more (e.g., once or more) during the note-on period is judged to be a pass note. A note whose difference falls within an allowable range less than a predetermined number of times during the note-on period is judged to be a fail note. If the total number of notes to be sung is 128 and the number of pass notes is 96, 75 points is calculated as the evaluation of the singing voice.

[0019] The display means 27 displays an overall evaluation based on the evaluation of the narration voice and the evaluation of the singing voice. For example, if the evaluation of the narration voice by the narration evaluation means 24 is 12 points and the evaluation of the singing voice by the singing evaluation means 26 is 75 points, the evaluation of the narration voice and the evaluation of the singing voice are added together and a total evaluation of 87 points is displayed on the monitor 12. This allows the content of the narration spoken by the singer himself to be reflected in the singing evaluation of the singer. Note that the method of calculating the overall evaluation by the display means 27 is not limited to the method of calculating the overall evaluation by adding up the evaluation of the narration voice and the evaluation of the singing voice.

[0020] The narration voice may be evaluated by subtracting a predetermined number from the number of words counted by the narration evaluation means 24, and the evaluation of the narration voice and the evaluation of the singing voice may be added together to obtain an overall evaluation. For example, when the predetermined number is set to 5 and the number of words counted by the narration evaluation means 24 is 1, -4 points are calculated as the evaluation of the narration voice, and -4 points are added to the evaluation of the singing voice of 75 points to calculate an overall evaluation of 71 points. As a result, when the content of the narration spoken by the singer does not match the music piece to be sung, the overall evaluation is lowered. When the judgment means 22 judges that no narration voice has been input, the display means 27 displays an overall evaluation on the monitor 12 based only on the evaluation result of the singing evaluation means 26.

[0021] Each process of the karaoke device 10 may be realized by software using a processor, or may be realized by a logic circuit (hardware) formed in an integrated circuit or the like. When a processor is used, the processor reads out and executes a program stored in a memory to perform various processes. For example, a CPU (Central Processing Unit) is used as the processor. Also, the memory is composed of one or more storage media such as a ROM (Read Only Memory) and a RAM (Random Access Memory) depending on the application.

[0022] The processing operation of the karaoke device of the first embodiment will be described with reference to Fig. 3. Fig. 3 is a flow diagram showing an example of the processing operation of the karaoke device of the first embodiment. Note that the symbols in Fig. 2 will be used as appropriate in the description. Also, the following flow is merely an example, and in particular the execution timing of the narration voice evaluation process and the singing voice evaluation process can be changed as appropriate.

[0023] As shown in Fig. 3, when the performance of the preceding music piece ends, the determination means 22 monitors whether or not there is voice input from the singer within a predetermined time before the performance of the subsequent music piece starts (step S01). If there is no voice input (No in step S01), the determination means 22 determines that there is no narration voice input, and the process proceeds to step S04. If there is voice input (Yes in step S01), the determination means 22 determines that there is narration voice input. The determination means 23 performs voice recognition processing, etc. on the narration voice, and identifies words from text data corresponding to the narration voice (step S02).

[0024] Next, when the performance means 25 detects the end of the narration voice (Yes in step S03), the performance means 25 starts karaoke performance of the song (step S04). The end of the narration voice is detected when a command to start performance is input from the karaoke device 10 or the remote control device 15, or when an instruction to start performance is input by the singer. When the karaoke performance starts, the narration evaluation means 24 evaluates the narration voice and the singing evaluation means 26 evaluates the singing voice in parallel. However, if the determination means 22 determines that no narration voice has been input, only the singing voice evaluation is performed.

[0025] In the narration voice evaluation process, the narration evaluation means 24 reads the lyrics data of the music piece from the storage means 21, and counts the number of predetermined words in the lyrics data that match the words identified by the identification means 23 to evaluate the narration voice (step S05). In the singing voice evaluation process, the singing evaluation means 26 reads the reference data of the music piece from the storage means 21, and evaluates the singing voice based on the comparison result between the note pitch of the reference data and the pitch of the singing voice (step S06). Then, when the karaoke performance by the performance means 25 ends (Yes in step S07), the display means 27 displays an overall evaluation on the monitor 12 based on the evaluation of the narration voice and the evaluation of the singing voice (step S08).

[0026] As described above, according to the first embodiment, when a voice is input by a singer before a musical piece is played, it is determined that the voice is a narration voice, and words identified from the narration voice are compared with predetermined words in the lyrics data. As a result, the narration voice is evaluated based on whether the content of the narration matches the content of the lyrics. In addition, the singing voice is evaluated based on the pitch of the singer's singing voice and the pitch of the notes of the musical piece. Then, a comprehensive evaluation is obtained from the evaluation of the narration voice and the evaluation of the singing voice. Therefore, the karaoke singing is evaluated comprehensively taking into account not only the singing ability of the singer but also the content of the narration spoken by the singer, and the content of the narration can be reflected in the singing evaluation.

[0027] <Second embodiment> Next, a karaoke device of a second embodiment will be described. The karaoke device of the second embodiment differs from the karaoke device of the first embodiment in that the narration voice is evaluated based on whether the contents of the narration match the melody. Therefore, the description of the second embodiment will be omitted for the same configuration as the first embodiment. Also, the symbols in FIG. 2 will be used appropriately here.

[0028] As described above, the storage means 21 of the karaoke device 10 of the second embodiment stores music data for each music ID. In addition to performance data, reference data, and lyric data, the music data includes predetermined words expressing the melody of the music, which are used as an evaluation criterion for the narration voice. In other words, in the second embodiment, instead of the predetermined words included in the lyric data, the predetermined words expressing the melody of the music are used in the evaluation process for the narration voice. In this case, the predetermined words expressing the melody are set based on the melody, chords, pitch, tempo, number of notes, etc. of the music.

[0029] For example, music data that includes major key melodies and chords, many high notes, and familiar scales includes predetermined words such as "cheerful," "lively," and "fun." Music data that includes minor key melodies and chords, many low notes, and questionable scales includes predetermined words such as "dark," "lonely," and "painful." Music data that has a fast tempo or uses many sounds includes predetermined words such as "hectic" and "intense," while music data that has a slow tempo or uses few sounds includes predetermined words such as "peaceful" and "calm."

[0030] Note that the music data does not have to include the predetermined words expressing the melody of the music. In this case, a table in which the predetermined words are associated with the tempo range may be prepared. For example, the tempo of 150 to 180 may be associated with predetermined words such as "running fast" and "speed". Also, a table in which the predetermined words are associated with the ratio of minor chords to major chords in the music may be prepared. For example, the minor chord 2:major chord 8 may be associated with predetermined words such as "fun" and "refreshing". Then, the predetermined words may be extracted from the table based on the tempo and chord structure of the music data.

[0031] The narration evaluation means 24 evaluates the narration voice based on the comparison result between the words identified by the identification means 23 and the predetermined words expressing the melody of the music. Specifically, words such as "lovely" and "sad" identified from the narration voice are compared with the predetermined words expressing the melody of the music. If the predetermined words expressing the melody of the music include words such as "lovely" and "sad", the number of these words is counted to evaluate the narration voice. For example, if the number of words is 12, 12 points are calculated as the evaluation of the narration voice.

[0032] As described above, according to the second embodiment, the words identified from the narration voice are compared with the predetermined words expressing the melody of the music. As a result, the narration voice is evaluated based on whether the contents of the narration match the melody. The evaluation of the narration is reflected in the singing evaluation, so that the karaoke singing can be evaluated comprehensively.

[0033] <Third embodiment> Next, a karaoke device of a third embodiment will be described with reference to Fig. 4 and Fig. 5. Fig. 4 is a functional block diagram of the karaoke device of the third embodiment. Fig. 5 is a diagram showing an example of a narration history, an appropriate time table, and an evaluation table. The karaoke device of the third embodiment differs from the karaoke device of the first embodiment in that it evaluates the narration time in addition to evaluating the singing voice and the narration voice. Therefore, the description of the same configuration as the first embodiment will be omitted for the third embodiment.

[0034] As shown in Fig. 4, the karaoke device 30 of the third embodiment is provided with a device main body 31, a monitor 32, a speaker 33, a microphone 34, and a remote control device 35, similar to the karaoke device 10 of the first embodiment. The device main body 31 is provided with a storage means 41, a determination means 42, a specification means 43, a narration evaluation means 44, a performance means 45, a singing evaluation means 46, and a display means 47. The device main body 31 is further provided with a generation means 48, a setting means 49, a measurement means 51, and a narration time evaluation means 52. The device main body 31 also stores a narration history, an appropriate time table, and an evaluation table, which will be described later.

[0035] The generating means 48 generates information on the presence or absence of narration voice input in the order of performance of the songs based on the determination result of the determining means 42. Specifically, the generating means 48 associates the determination result of the determining means 42 with the performance order to generate a narration history. When the determining means 42 determines that narration voice has been input before a song is played, the generating means 48 associates "present" as the presence or absence information with the performance order of the song. When the determining means 42 determines that narration voice has not been input before a song is played, the generating means 48 associates "absence" as the presence or absence information with the performance order of the song.

[0036] For example, the narration history shown in Fig. 5(A) is associated with a performance order indicating how many songs were performed before the current song, and information on whether narration voice was input for each song. Three songs have already been performed so far, and it is determined that narration voice was input for the songs one and two songs ago, and that narration voice was not input for the song three songs ago. Note that the narration history may be generated for all songs performed so far, or may be generated while being updated for songs up to a predetermined number of songs before the current song (for example, five songs before).

[0037] The setting means 49 sets the appropriate time for the narration voice based on the presence / absence information generated by the generating means 48. Specifically, before the performance of a song begins, the setting means 49 sets the appropriate time for the narration voice by referring to the appropriate time table. In the appropriate time table, combinations of whether or not narration voice has been input for up to two songs prior to the current song are associated with appropriate narration times. Therefore, the setting means 49 sets the appropriate time for the narration voice for the current song based on the presence / absence information for up to two songs prior to the current song in the narration history and the appropriate time table.

[0038] For example, in the appropriate time table shown in FIG. 5(B), the combination of narration "Any" and "Any" for two songs before and one song before is associated with an appropriate narration time of 60 seconds. The combination of narration "Yes" and "Any" for two songs before and one song before is associated with an appropriate narration time of 40 seconds. The combination of narration "Any" and "Yes" for two songs before and one song before is associated with an appropriate narration time of 20 seconds. The combination of narration "Yes" and "Yes" for two songs before and one song before is associated with an appropriate narration time of 0 seconds.

[0039] If there is no narration for two consecutive songs, the appropriate narration time may be set to be longer since it indicates that the attendees would like to take a break. If there is narration for two consecutive songs, the appropriate narration time may be set to be shorter since it indicates that the attendees find the narration annoying. Here, if the narration voice presence information for the song two songs before and the song before is a combination of "absent" and "present," the setting means 49 refers to the appropriate time table and sets the appropriate narration time to 20 seconds.

[0040] The measuring means 51 measures the actual narration time from the start of input of the narration voice to the start of playing the music. Specifically, the actual narration time is measured from the time when the determining means 42 determines that the narration voice is input to the time when the playing means 45 starts playing. Note that the longest actual narration time may be set based on the appropriate narration time, and the playing means 45 may start playing the music when the longest actual narration time has elapsed before the end of the input of the narration voice is detected. In this case, the measuring means 51 measures the longest actual narration time as the actual narration time.

[0041] The narration time evaluation means 52 evaluates the narration time based on the result of comparing the actual narration time with the appropriate narration time. Specifically, the narration time evaluation means 52 evaluates the narration time by referring to an evaluation table. In the evaluation table, an evaluation value is associated with the deviation rate (error rate) of the actual narration time from the appropriate narration time. Therefore, the deviation rate of the actual narration time from the appropriate narration time is calculated, and the narration time is evaluated based on the deviation rate of the actual narration time and the evaluation table.

[0042] For example, in the evaluation table shown in FIG. 5(C), the deviation rate "less than 10%" is associated with an evaluation value of "+5", and the deviation rate "10% or more and less than 20%" is associated with an evaluation value of "+2". The deviation rate "20% or more and less than 30%" is associated with an evaluation value of "0", and the deviation rate "less than 30%" is associated with an evaluation value of "-5". Here, if the appropriate narration time is 60 seconds and the actual narration time is 52 seconds, the deviation rate is about 13%, so the narration evaluation means 44 evaluates the evaluation value as +2. The deviation rate is calculated by (appropriate narration time-actual narration time) / appropriate narration time×100.

[0043] The display means 47 displays an overall evaluation based on the evaluation of the narration voice, the evaluation of the narration time, and the evaluation of the singing voice. For example, if the evaluation of the narration voice by the narration evaluation means 44 is 8 points, the evaluation of the narration time by the narration time evaluation means 52 is -5 points, and the evaluation of the singing voice by the singing evaluation means 46 is 82 points, the sum of these is displayed as 85 points on the monitor 32 as the overall evaluation. This allows the content of the narration spoken by the singer himself and the length of the narration taking into account the atmosphere of the place to be reflected in the singing evaluation of the singer.

[0044] The processing operation of the karaoke device of the third embodiment will be described with reference to Fig. 6. Fig. 6 is a flow diagram showing an example of the processing operation of the karaoke device of the third embodiment. Note that the symbols in Fig. 4 will be used as appropriate in the description. It is also assumed that the karaoke device has already generated a narration history for the past several performances. Furthermore, the following flow is merely an example, and the timing of the evaluation process of the narration voice, the evaluation process of the narration time, and the evaluation process of the singing voice can be changed as appropriate.

[0045] 6, when the performance of the preceding music piece ends, the determination means 42 monitors whether or not there is voice input from the singer within a predetermined time before the performance of the subsequent music piece starts (step S11). If there is no voice input (No in step S11), the determination means 42 determines that there is no narration voice input, and the process proceeds to step S15. If there is voice input (Yes in step S11), the determination means 42 determines that there is narration voice input, and the measurement means 51 starts measuring the narration real time immediately after the determination (step S12).

[0046] Next, the identifying means 43 performs voice recognition processing on the narration voice, and identifies words from the text data corresponding to the narration voice (step S13). Next, when the performance means 45 detects the end of the narration voice (Yes in step S14), the measuring means 51 ends the measurement of the narration real time, and the performance means 45 starts karaoke performance of the song (step S15). The end of the narration voice is detected when a command to start performance is input from the karaoke device 30 or the remote control device 35, or when a singer inputs a voice instruction to start performance.

[0047] When karaoke performance is started, the narration voice evaluation process by the narration evaluation means 44, the singing voice evaluation process by the singing evaluation means 46, and the narration time evaluation process by the narration time evaluation means 52 are carried out in parallel. However, if the determination means 42 determines that no narration voice has been input, only the singing voice evaluation process is carried out. At the timing of this evaluation process, the generation means 48 may generate a narration history (information on whether or not narration voice has been input) for the current song in order to further evaluate the narration time when the subsequent song is played.

[0048] In the narration voice evaluation process, the narration evaluation means 44 reads the lyric data of the song from the storage means 41, and counts the number of predetermined words in the lyric data that match the words identified by the identification means 43 to evaluate the narration voice (step S16). In the singing voice evaluation process, the singing evaluation means 46 reads the reference data of the song from the storage means 41, and evaluates the singing voice based on the comparison result between the note pitch of the reference data and the pitch of the singing voice (step S17).

[0049] In the narration time evaluation process, the narration time evaluation means 52 reads out information on the presence or absence of narration voice for the song two songs before and one song before from the narration history, and sets the appropriate time of the narration voice for the song from the appropriate time table (step S18). Next, the narration time evaluation means 52 calculates the deviation rate of the actual narration time from the appropriate narration time, and evaluates the narration time from the deviation rate of the actual narration time and the evaluation table (step S19). Then, when the karaoke performance by the performance means 45 ends (Yes in step S20), the display means 47 displays an overall evaluation on the monitor 32 based on the evaluation of the narration voice, the evaluation of the singing voice, and the evaluation of the narration time (step S21).

[0050] As described above, according to the third embodiment, the appropriate narration time that matches the atmosphere of the venue is calculated based on the narration history that indicates the presence or absence of narration in the order of music performance, and the appropriate length of the narration is evaluated based on the actual time of the narration and the appropriate time. The content of the narration spoken by the singer and the appropriate length of the narration are reflected in the singing evaluation, allowing a comprehensive evaluation of the karaoke singing.

[0051] The narration evaluation means is not particularly limited in the evaluation method as long as it is a method for evaluating the narration voice based on the comparison result between the word specified by the specification means and the predetermined word. For example, the narration evaluation means may evaluate the narration voice by combining the comparison result between the word specified by the specification means and the predetermined word included in the lyrics data of the music piece, and the comparison result between the word specified by the specification means and the predetermined word expressing the melody of the music piece. This allows the content of the narration spoken by the singer to be evaluated in more detail.

[0052] The display means may display the evaluation of the narration voice, the evaluation of the narration time, and the evaluation of the singing voice separately, so that the singer can understand whether the content of the narration was appropriate and whether the narration took into consideration the atmosphere of the place.

[0053] In each embodiment and each modification, a program may be installed in the karaoke device to add a function for evaluating the narration voice and / or the narration time to the karaoke device. The program is stored in a storage medium. The storage medium is not particularly limited, and may be a non-transitory storage medium such as an optical disk, a magneto-optical disk, or a flash memory.

[0054] Although the present embodiment has been described, other embodiments may be obtained by combining the above-described embodiments and modifications in whole or in part.

[0055] In addition, the technology of the present invention is not limited to the above-mentioned embodiment, and may be variously changed, substituted, or modified within the scope of the gist of the technical idea. Furthermore, if the technical idea can be realized in a different way due to the progress of technology or a different technology derived therefrom, it may be implemented using that method. Therefore, the claims cover all embodiments that can be included in the scope of the technical idea. [Explanation of symbols]

[0056] 10, 30: Karaoke equipment 22, 42: Judgment means 23, 43: Specification means 24, 44: Narration evaluation measures 25, 45: Performance means 26, 46: Singing evaluation instruments 27, 47: Display means 48: Generation means 49: Setting method 51: Measurement methods 52: Narration time evaluation method

Claims

1. a determination means for determining whether or not a narration voice has been input in response to a voice input within a predetermined time before the performance of a musical piece; a determination means for determining words from the narration voice by a voice recognition process when the narration voice is input; a narration evaluation means for evaluating a narration voice based on the number of predetermined words in the lyrics data of the music piece that match the words specified by the specifying means and / or the number of predetermined words expressing the melody of the music piece that match the words specified by the specifying means; a performance means for starting performance of a piece of music by detecting the end of the narration voice; a singing evaluation means for evaluating the singing voice based on a comparison result between the pitch of the singing voice and the pitch of notes included in the reference data of the musical piece; and a display means for displaying an overall evaluation based on the evaluation of the narration voice and the evaluation of the singing voice.

2. a generating means for generating information on the presence or absence of input of a narration voice based on a result of the determination by the determining means in the order in which the music piece is played; a setting means for setting an appropriate duration of the narration voice based on the presence / absence information generated by the generating means; A measuring means for measuring an actual narration time from the start of input of a narration voice to the start of playing a piece of music; a narration time evaluation means for evaluating a narration time based on a comparison result between an actual narration time and an appropriate narration time, 2. The karaoke apparatus according to claim 1, wherein the display means displays a comprehensive evaluation based on the evaluation of the narration voice, the evaluation of the narration time, and the evaluation of the singing voice.

Images