JP6650248B2 - Singing evaluation method, singing evaluation program, singing evaluation device, and singing evaluation system - Google Patents

Description

  The present invention relates to a singing evaluation method, a singing evaluation program, a singing evaluation device, and a singing evaluation system.

  Conventionally, various methods for scoring the skill of a user's singing have been proposed. For example, Patent Literature 1 below proposes a method of comparing a pitch (pitch) extracted based on user voice data with a pitch based on musical sound data to determine the accuracy of the user's pitch. Have been.

JP 2005-128372 A

  If the pitch is correct, the singer will be singing correctly with respect to the pitch. However, the skill of singing is not judged only by the accuracy of the pitch of the singing voice. As for the skill of singing, it is also necessary to judge the timing at which the singing voice is interrupted and the length of the singing voice. The timing at which the singing voice is interrupted and the length of the singing voice depend on the breathing interval of the user. By devising the breathing section, the user can lengthen the singing voice, increase the singing voice, and provide a wider range of expression. In the determination method according to Patent Literature 1, such a user's breathing section is not evaluated.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a singing evaluation method, a singing evaluation program, a singing evaluation device, and a singing evaluation system capable of evaluating a user's respiratory interval.

A singing evaluation method according to the present invention that achieves the above object is a singing evaluation method for evaluating the skill of a user singing. The singing evaluation method specifies a frequency of the target voice that changes over time from target voice data indicating a target voice targeted by the user, and performs a time transition from user voice data indicating a user voice that is the voice of the user. A frequency specifying step of specifying a frequency of the user voice. Singing evaluation method, on the basis of the frequency of the target speech, the frequency have your target speech over the evenly scattered wide range identifies the breathing segment that exist innumerable frequency as target respiration interval, the user based on the frequency of the audio, with a breathing segment specifying step of the frequency have your user speech to identify the breathing segment that exist are countless frequency over a wide range scattered without evenly as a user breathing segment. The singing evaluation method includes a breathing section comparing step of comparing the target breathing section and the user breathing section, and an output step of outputting a result compared in the breathing section comparing step.

  A singing evaluation program according to the present invention that achieves the above object is a singing evaluation program for causing a computer to execute the above-described singing evaluation method.

A singing evaluation device according to the present invention that achieves the above object is a singing evaluation device that evaluates a user's singing skill. The singing evaluation device specifies the frequency of the target voice that makes a time transition from the target voice data that represents the target voice targeted by the user, and makes a time transition from the user voice data that represents the user voice that is the user's voice. A frequency specifying unit that specifies a frequency of the user voice; Singing evaluation device, based on the frequency of the target speech, the frequency have your target speech over the evenly scattered wide range identifies the breathing segment that exist innumerable frequency as target respiration interval, the user based on the frequency of the audio, including respiratory section identifying unit that the frequency have your user speech to identify the breathing segment that exist are countless frequency over a wide range scattered without evenly as a user breathing segment. The singing evaluation device includes a breathing section comparison unit that compares the target breathing section and the user breathing section, and an output unit that outputs a result compared by the breathing section comparison unit.

  The singing evaluation system according to the present invention that achieves the above object has a user terminal that generates user voice data from a user voice that is a user voice and transmits the user voice data via a network. The singing evaluation system receives the user voice data from the user terminal, compares the user voice data with target voice data representing a target voice targeted by the user, and transmits a singing evaluation result. It has a server device that functions as a singing evaluation device. The user terminal receives a result of the singing evaluation from the server device, and outputs the result.

  According to the above-described singing evaluation method, singing evaluation program, singing evaluation device, and singing evaluation system, the target breathing section is specified based on the frequency of the target voice. Further, the user breathing section is specified based on the frequency of the user voice. Then, the target breathing section is compared with the user breathing section, and a comparison result is output. For this reason, the user can grasp the deviation of the user breathing section from the target breathing section. Therefore, it is possible to provide a singing evaluation method, a singing evaluation program, a singing evaluation device, and a singing evaluation system that can evaluate a user's breathing section.

It is a block diagram showing the schematic structure of the singing evaluation device concerning this embodiment. It is a block diagram which shows the functional structure of CPU of a singing evaluation apparatus. It is a figure showing an example of change of the frequency of the voice accompanying time transition. It is a figure showing an example of a change of a voice level accompanying time transition. It is a flowchart which shows the singing evaluation method which concerns on this embodiment. FIG. 9 is a diagram illustrating an example of a result displayed on a display unit. It is a figure showing a mode that a respiratory section, a pitch (frequency), and a loudness (level) of a voice can be selected. It is a block diagram showing a schematic structure of a singing evaluation system.

  Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the description of the drawings, the same elements will be denoted by the same reference symbols, without redundant description. In addition, the dimensional ratios in the drawings are exaggerated for convenience of description, and may be different from the actual ratios.

  FIG. 1 is a block diagram illustrating a schematic configuration of a singing evaluation device 100 according to the present embodiment.

  The singing evaluation device 100 is a computer terminal such as a desktop PC (Personal Computer) or a notebook PC. The singing evaluation device 100 may be incorporated in a part of a karaoke device or the like. The singing evaluation device 100 receives a user's voice input and evaluates the user's singing skill.

  The singing evaluation device 100 includes a CPU (Central Processing Unit) 110, a memory 120, a hard disk 130, a communication I / F unit 140, a display unit 150, an operation unit 160, a voice input unit 170, and a voice output unit 180. The components are connected to each other via a bus 190 so that they can communicate with each other.

  The CPU 110 controls each component and executes various arithmetic processes according to programs stored in the memory 120 and the hard disk 130.

  The memory 120 includes a ROM (Read Only Memory) for storing various programs and various data, a RAM (Random Access Memory) for temporarily storing programs and data as a work area, and the like.

  The hard disk 130 stores various programs including an operating system and various data. The hard disk 130 stores music data including target audio data representing target audio targeted by the user, and accompaniment data for providing accompaniment sounds to the user. In this specification, the target voice means, for example, a voice sung by a professional singer, but is not particularly limited as long as the voice is sung by a person who becomes a model of the song. Further, the hard disk 130 stores user voice data representing user voice, which is voice of the user. Further, the hard disk 130 stores information of advice related to the singing evaluation result.

  The communication I / F unit 140 is an interface for communicating with other devices via a network, and uses standards such as Ethernet (registered trademark), FDDI (Fiber Distributed Data Interface), and Wi-Fi (Wireless Fidelity). . The communication I / F unit 140 receives music data including target voice data and accompaniment data, and information on advice related to the singing evaluation result from an external server or the like.

  The display unit 150 is, for example, a liquid crystal display, and displays various information such as a singing evaluation result.

  The operation unit 160 is, for example, a pointing device such as a mouse or a keyboard, and is used by a user to input various information.

  The audio input unit 170 includes a microphone that converts a user's voice into an electric signal, an amplifier that amplifies the converted electric signal, an A / D converter that converts an electric signal from an analog signal to a digital signal, and the like. That is, the user voice is converted into a digital signal by the voice input unit 170, and the converted digital signal is processed as user voice data by the CPU 110.

  The audio output unit 180 includes a D / A converter that converts an electric signal from a digital signal to an analog signal, an amplifier that amplifies the electric signal, a speaker or a headphone that converts the electric signal into sound and outputs sound.

  A part or all of the configuration of the voice input unit 170 and the voice output unit 180 may be provided outside the singing evaluation device 100, and is not limited to the example illustrated in FIG. For example, a part of the configuration of the voice input unit 170 and the voice output unit 180 may be connected to the singing evaluation device 100 via a voice input terminal and a voice output terminal provided in the singing evaluation device 100.

  FIG. 2 is a block diagram showing a functional configuration of CPU 110 of singing evaluation apparatus 100.

  By executing various programs, the CPU 110 executes, for example, the frequency identification unit 111, the breathing interval identification unit 112, the level identification unit 113, the accompaniment data reproduction unit 114, the breathing interval comparison unit 115, the frequency comparison unit 116, and the level comparison unit 117. , And the output unit 118. Hereinafter, each functional configuration will be described.

  The frequency specifying unit 111 specifies the frequency of the target sound that undergoes time transition from the target sound data. Further, the frequency specifying unit 111 specifies the frequency of the user voice that changes over time from the user voice data. Specifically, the frequency identification unit 111 applies Fourier transform to the target audio data and the user audio data, respectively. Then, the frequency specifying unit 111 specifies the frequency component of the audio at predetermined time intervals, and specifies the lowest frequency among the specified frequency components as the “basic frequency”. The fundamental frequency of a voice corresponds to the pitch (pitch) of a sound felt by humans. The specified frequency component can be expressed, for example, as shown in FIG.

  FIG. 3 is a diagram illustrating an example of a change in the frequency of the voice according to the time transition. The frequency specifying unit 111 specifies the frequency of the voice at predetermined time intervals according to the progress of the singing (the progress of time), so that a change in the frequency of the voice accompanying the time transition is confirmed. Here, the predetermined time is arbitrary, for example, 0.1 second. The shorter the predetermined time is, the more precisely the transition of the voice frequency can be specified. Of the frequency components shown in FIG. 3, the lowest frequency component indicated by arrow A is the fundamental frequency, and the frequency component indicated by arrow B is the frequency of the overtone.

  Returning to FIG. 2, the breathing section specifying unit 112 specifies the breathing section in the target voice as the target breathing section based on the frequency of the target voice. In addition, the breathing section specifying unit 112 specifies a breathing section in the user voice as a user breathing section based on the frequency of the user voice. The respiratory interval specifying unit 112 specifies, as indicated by an arrow C in FIG. 3, a portion where the frequencies are scattered uniformly as a respiratory interval. More specifically, the respiratory section identification unit 112 is not a section in which a specific frequency exists, such as a fundamental frequency indicated by an arrow A or a frequency of an overtone indicated by an arrow B, but has an infinite number of frequencies over a wide range. Is specified as a respiratory section. The sound at the time of breathing has no specific frequency component and is dispersed, so that such a dispersed portion can be specified as a breathing section.

  The level specifying unit 113 specifies the level of the target sound that changes with time from the target sound data. Further, the level specifying unit 113 specifies the level of the user voice that changes over time from the user voice data. The level identification unit 113 identifies the audio level of the target audio data and the user audio data at predetermined time intervals. The sound level corresponds to the strength (sound pressure) of the sound. The audio level can be expressed, for example, as shown in FIG.

  FIG. 4 is a diagram illustrating an example of a change in the level of the voice according to the time transition. The level specifying unit 113 specifies the audio level at predetermined time intervals according to the progress of the singing (the progress of time), so that a change in the audio level due to the time transition is confirmed. Here, the predetermined time is arbitrary, for example, 0.1 second. The shorter the predetermined time is, the more precisely the transition of the sound level can be specified.

  Returning to FIG. 2, the accompaniment data reproducing unit 114 reproduces the accompaniment data stored in the hard disk 130 or the like and included in the music data together with the target audio data in order to provide the accompaniment to the user. Then, the accompaniment data reproducing unit 114 outputs an electric signal based on the accompaniment data to the audio output unit 180, and causes the audio output unit 180 to output the music signal as an accompaniment sound. The user sings while listening to the accompaniment sound output by the audio output unit 180.

  The breathing section comparator 115 compares the target breathing section with the user's breathing section. Specifically, the breathing section comparison unit 115 compares the start and end timings of the target breathing section and the user's breathing section, respectively.

  The frequency comparing unit 116 compares the frequency of the target voice and the frequency of the user voice at the same timing of the singing song. Specifically, the frequency comparing unit 116 calculates the ratio of the frequency of the user voice to the frequency of the target voice at the same timing of the singing song. Note that the frequency comparison unit 116 may calculate the difference between the frequency of the target voice and the frequency of the user voice at the same timing of the singing song, instead of the ratio.

  The level comparing section 117 compares the level of the target voice and the level of the user voice at the same timing of the singing song. Since the target voice and the user voice are not recorded under the same condition, the level of the user voice may be lower or higher as a whole as compared with the level of the target voice. For this reason, for example, the comparison is performed according to the following procedure. First, the level comparison unit 117 calculates the average value of the target voice level and the user voice level in part or all of the singing, and calculates the ratio of the average value of the user voice level to the target voice level average value. Is calculated. Then, CPU 110 corrects the level of the target voice by multiplying the calculated ratio by the level of the target voice. Then, the CPU 110 compares the level of the corrected target voice with the level of the user voice at the same timing of the singing proceeding. Specifically, the level comparing section 117 obtains the ratio of the level of the user voice to the level of the corrected target voice at the same timing of the singing song. Note that the level comparing section 117 may calculate the difference between the corrected target voice level and the user voice level at the same timing of the singing song in progress, instead of the ratio.

  The output unit 118 outputs the result obtained by the respiratory interval comparison unit 115, the frequency comparison unit 116, and the level comparison unit 117 to the display unit 150. Specifically, it is as follows.

  When the difference between the start and end timings of the target breathing section and the user breathing section is small in the comparison result by the breathing section comparing section 115, the output section 118 determines that the singing is good. On the other hand, when the difference between the start and end timings of the target breathing section and the user breathing section is large in the comparison result by the breathing section comparing section 115, the output section 118 determines that the singing is poor. Then, the output unit 118 displays advice related to the comparison result of the breathing sections on the display unit 150.

  In the comparison result by the frequency comparing unit 116, the closer the ratio of the frequency of the user voice to the frequency of the target voice is to 1, the output unit 118 determines that the singing is better. Then, the output unit 118 displays advice related to the frequency comparison result on the display unit 150.

  In the comparison result by the level comparing unit 117, the closer the ratio of the level of the user voice to the corrected level of the target voice is closer to 1, the output unit 118 determines that the singing is good. Then, the output unit 118 displays advice related to the frequency comparison result on the display unit 150.

  The output unit 118 has a function of scoring based on the results obtained by the respiratory interval comparison unit 115, the frequency comparison unit 116, and the level comparison unit 117. For example, if the breathing section is shifted by 0.1 second, a rule such as minus one point is determined in advance, and the minus points for all sections of the music are totaled and deducted from 100 points. The output unit 118 outputs the score as the scoring result to the display unit 150.

  Next, a singing evaluation method according to the present embodiment will be described with reference to FIG. FIG. 5 is a flowchart illustrating the singing evaluation method according to the present embodiment. The process shown in the flowchart of FIG. 5 is stored as a program in the memory 120 or the hard disk 130 of the singing evaluation device 100, and is executed by the CPU 110. The program of the singing evaluation device 100 according to the present embodiment evaluates the user's singing skill by comparing the user voice data with the target voice data.

  First, the CPU 110, as the frequency specifying unit 111, specifies a frequency of a target sound that changes over time from target sound data included in music data stored in the hard disk 130 (step S101). Specifically, the CPU 110 specifies a fundamental frequency of a target sound that undergoes a time transition (hereinafter, referred to as a target fundamental frequency) at predetermined time intervals. After specifying the target basic frequency, the CPU 110 causes the memory 120 or the like to store information in which the time at which the target basic frequency is specified in the target audio data is associated with the target basic frequency.

  Next, the CPU 110, as the breathing section specifying unit 112, specifies the target breathing section based on the target basic frequency specified in step S101 (step S102). Specifically, the CPU 110 specifies a target breathing section for each time of breathing in the target voice in the target voice data. After specifying the target breathing section, the CPU 110 causes the memory 120 or the like to store information that associates the time at which the breathing section was specified in the target voice with the breathing section at each time.

  Next, the CPU 110, as the level identification unit 113, identifies the level of the time-shifted target audio from the target audio data (step S103). Specifically, the CPU 110 specifies a level of a target sound that changes over time (hereinafter, referred to as a target level) at predetermined time intervals. After specifying the target level, the CPU 110 causes the memory 120 or the like to store information that associates the time at which the target level was specified in the target audio data with the target level.

  Through steps S101 to S103 up to this point, the features of the target voice targeted by the user are specified. The above steps are not performed in succession to the following steps, but are executed in advance, and the target breathing period, the frequency and the level of the target sound may be stored in the hard disk 130 or the like.

  Next, the CPU 110 plays the accompaniment sound based on the accompaniment data from the audio output unit 180 as the accompaniment data playback unit 114 (step S104). The user sings via the voice input unit 170 while listening to the accompaniment sound.

  The CPU 110 acquires the user voice data via the voice input unit 170 during the singing of the user (while the accompaniment sound is being reproduced) (step S105).

  Next, the CPU 110, as the frequency specifying unit 111, specifies the frequency of the user voice that undergoes a time transition from the user voice data acquired in step S105 (step S106). Specifically, the CPU 110 specifies a fundamental frequency of a user voice that changes over time (hereinafter, referred to as a user fundamental frequency) at predetermined time intervals. After specifying the user basic frequency, the CPU 110 causes the memory 120 or the like to store information that associates the time at which the user basic frequency was specified in the user voice data with the user basic frequency.

  Next, the CPU 110 specifies the user's breathing section as the breathing section specifying unit 112 based on the user's fundamental frequency specified in step S106 (step S107). Specifically, the CPU 110 specifies a user breathing section for each section of the user voice data that is breathing in the user voice. After specifying the user's breathing section, the CPU 110 causes the memory 120 or the like to store information relating the time at which the breathing section was specified in the user's voice and the breathing section at each time.

  Next, the CPU 110, as the level specifying unit 113, specifies the level of the user voice that changes over time from the user voice data acquired in step S105 (step S108). Specifically, the CPU 110 specifies a level of a user voice that changes over time (hereinafter, referred to as a user level) at predetermined time intervals. After specifying the user level, the CPU 110 causes the memory 120 or the like to store information that associates the time at which the user level was specified in the user voice data with the user level.

  Next, the CPU 110, as the breathing section comparison unit 115, compares the target breathing section specified in step S102 with the user breathing section specified in step S107 (step S109). Specifically, CPU 110 refers to the information stored in memory 120 or the like in steps S102 and S107, and compares the start timing and end timing of the target respiratory section and the user's respiratory section associated with the same time. This process is performed on all the user breathing sections specified in step S107, that is, on the entire user voice.

  Next, the CPU 110, as the frequency comparing unit 116, compares the target fundamental frequency specified in step S101 and the user fundamental frequency specified in step S106 at the same timing of the singing song that is going on (step S110). Specifically, CPU 110 refers to the information stored in memory 120 or the like in steps S101 and S106, and compares the target fundamental frequency and the user frequency associated with the same time. This process is performed on all the user fundamental frequencies specified in step S106, that is, on the entire user voice.

  Next, the CPU 110, as the level comparing unit 117, compares the target level specified in Step S103 and the user level specified in Step S108 at the same timing of the singing song (Step S111). Specifically, CPU 110 refers to the information stored in memory 120 or the like in steps S103 and S108, and compares the target level and the user level associated with the same time. This process is executed for all the user levels specified in step S108, that is, for the entire user voice.

  Next, the CPU 110 outputs the comparison results in steps S109, S110, and S111 to the display unit 150 as the output unit 118, as shown in FIG. 6 (step S112). FIG. 6 is a diagram illustrating an example of a result displayed on the display unit 150. In FIG. 6, a thick line indicates a target fundamental frequency, and a thin line indicates a user fundamental frequency. When displaying on the display unit 150, it is preferable to display not by frequency but by pitch so that the user can easily understand the skill of his or her singing.

  FIG. 6 shows the result when the breathing interval before singing the lyrics “Morinonaka” is short, the voice at the time of the lyrics “A” is low, and the voice at the time of the lyrics “No” is extremely high. In the case of such a result, the advice based on the comparison result is displayed at a corresponding portion where the user voice is different from the target voice. For example, advice such as "long breathing" is displayed at a place where the breathing section is short. Further, each comparison result can be converted into a numerical value and displayed as a score. FIG. 6 shows an example in which “94 points” is displayed at the upper left. In addition, it is preferable that the breakdown of the minus portion from 100 points is displayed. For example, FIG. 6 shows a case where the breakdown of minus 6 points from 100 points is a respiratory section: -2 points, a frequency (pitch): -2 points, and a level: -2 points.

  In FIG. 6, the lyrics of the music are also displayed. The lyrics may be displayed in their entirety, but may be displayed in part as shown in FIG. In this case, the previous or subsequent lyrics can be displayed by switching the screen or scrolling.

  As described above, according to the singing evaluation method and the singing evaluation device according to the present embodiment, the breathing section in the target voice is specified as the target breathing section based on the frequency of the target voice. Further, based on the frequency of the user voice, a breathing section in the user voice is specified as a user breathing section. Then, the target breathing section is compared with the user breathing section, and a comparison result is output. For this reason, the user can grasp the deviation of the user breathing section from the target breathing section. Therefore, the respiratory interval can be evaluated.

  In addition, the frequency of the target voice and the frequency of the user voice at the same timing of the singing song can be compared, and the frequency comparison result can be output. For this reason, the deviation of the frequency of the user voice from the frequency of the target voice can be grasped. Therefore, not only the evaluation of the breathing section but also the evaluation of the frequency can be performed, and the singing can be evaluated more precisely.

  Further, a time-shifted target level is specified from the target voice data, a time-shifted user level is specified from the user voice data, and the target level and the user level at the same timing of the singing song are compared. Can output the result. For this reason, it is possible to grasp the difference between the level of the user voice and the level of the target voice. Therefore, not only the evaluation of the breathing section and the frequency, but also the evaluation of the level can be performed, and the singing can be evaluated more precisely.

  The comparison result is displayed on the display unit 150 as a score. Therefore, it is easy for the user to judge the skill of the singing.

  Further, advice related to the comparison result is displayed on the display unit 150. For this reason, it becomes easy for the user to grasp the weak points.

  Note that the present invention is not limited to the above-described embodiment, and can be variously modified within the scope of the claims.

  For example, in the above-described embodiment, all of the user breathing section, the frequency of the user voice, and the user level were compared. However, as shown in FIG. 7, three items of a breathing section, a pitch (frequency), and a loudness (level) may be used as a checklist so that the user can appropriately select an item to be evaluated. . As a result, it is possible to evaluate an item that the user perceives to be weak and to improve the singing ability of the user by practicing the item with emphasis.

  Further, in the above-described embodiment, the frequency comparing unit 116 compares the target fundamental frequency and the user fundamental frequency, and evaluates a shift in pitch. However, the frequency comparison unit 116 may additionally or alternatively compare the timings of a place where the scale rises, a place where the scale falls, and the vibrato. By evaluating such items, more accurate singing evaluation can be performed.

  In the above-described embodiment, the singing evaluation device 100 compares the target fundamental frequency and the user fundamental frequency in the singing evaluation method illustrated in FIG. However, the present invention is not limited to this, and frequencies other than the fundamental frequency may be compared. For example, the singing evaluation device 100 may compare the frequency of the second overtone of the target voice with the frequency of the second overtone of the user voice.

  In the above-described embodiment, the singing evaluation method of evaluating the singing of the user after the user sings the music from the beginning to the end has been described. However, the present invention is not limited to this, and the singing may be evaluated in real time while the user sings. At this time, for example, when the user's breathing section is deviated from the target breathing section, a buzzer may be sounded to warn or the display section 150 may indicate that.

  In the above-described embodiment, the step S108 for specifying the level of the user voice is executed after the step S106 for specifying the frequency of the user voice and the step S107 for specifying the user's breathing interval. However, the present invention is not limited to this. The step S108 for specifying the level of the user voice may be performed in parallel with or before the step S106 for specifying the frequency of the user voice and the step S107 for specifying the user's breathing interval. It may be performed.

  In addition, the singing evaluation result in the above-described embodiment may be stored in the hard disk 130 as data. Since the singing evaluation result can be stored as data in this way, the user can confirm daily singing improvement.

  Further, in the above-described embodiment, the step S103 for specifying the level of the target voice, the step S108 for specifying the level of the user voice, the step S110 for comparing the target basic frequency and the user basic frequency, and the step for comparing the target level and the user level S111 may be omitted.

<Modification 1>
Hereinafter, modified examples of the above-described embodiment will be described.

  In the above embodiment, the singing evaluation device 100 alone acquires user voices and performs singing evaluation. In the first modification, the singing evaluation system including a plurality of devices acquires user voices and evaluates singing.

  FIG. 8 is a block diagram showing a schematic configuration of the singing evaluation system 200.

  The singing evaluation system 200 includes a PC 210, a portable terminal 220, and a server device 230, as shown in FIG.

  The PC 210 is a computer terminal such as a desktop PC or a notebook PC.

  The mobile terminal 220 is a terminal that can be carried by a user, such as a tablet terminal or a smartphone.

  The PC 210 and / or the mobile terminal 220 function as a user terminal.

  The server device 230 is an information processing device that executes the singing evaluation method. The server device 230 has substantially the same hardware configuration as the singing evaluation device 100 shown in FIG. Further, the server device 230 has a configuration similar to the functional configuration of the CPU 110 of the singing evaluation device 100 shown in FIG.

  The network 240 includes a LAN (Local Area Network) based on standards such as Ethernet (registered trademark), FDDI, and Wi-Fi, and a WAN (Wide Area Network) in which LANs are connected by a dedicated line. Note that the type and number of each component connected to the network 240 are not limited to the example shown in FIG.

  The operation of the singing evaluation system 200 will be described.

  The PC 210 or the portable terminal 220 as the user terminal acquires the accompaniment data from the server device 230. Hereinafter, a description will be given assuming that the portable terminal 220 has acquired the accompaniment data. The portable terminal 220 reproduces the accompaniment data and receives an input of a user voice. Here, the input of the user's voice may be performed through a microphone built in the portable terminal 220 or via a microphone connected to the portable terminal 220. The mobile terminal 220 generates user voice data from the input user voice. Then, the mobile terminal 220 transmits the user voice data to the server device 230 via the network 240.

  The server device 230 receives the user voice data generated in the mobile terminal 220 from the mobile terminal 220. Then, the server device 230 starts the singing evaluation method shown in FIG. The singing evaluation method shown in FIG. 5 has substantially the same steps as those in the above-described embodiment, and thus detailed description thereof will be omitted. The server device 230 compares the user voice and the target voice by the singing evaluation method, and transmits (outputs) the comparison result to the portable terminal 220 as a singing evaluation result.

  The mobile terminal 220 receives the result of the singing evaluation from the server device 230 and outputs the result. The output of the result of the singing evaluation in the mobile terminal 220 is executed, for example, by being displayed on the screen of the mobile terminal 220 or being uttered as voice.

  As described above, according to the singing evaluation system 200 according to the first modification, the acquisition of the user voice is performed by the user terminal such as the PC 210 or the mobile terminal 220, and the evaluation of the singing based on the user voice is performed by the server device 230. . There is no need to perform singing evaluation on the user terminal having relatively low processing capability. On the other hand, song evaluation can be performed by a server device having relatively high processing capability. In other words, a device with a high processing capacity can execute a process with a large processing load, and a device with a low processing capability can execute a process with a small processing load. Therefore, processing can be optimized.

  The user does not need to own a PC on which the singing evaluation program is installed or go to a place where the PC is located. That is, according to the singing evaluation system 200, the singing evaluation service can be easily provided using the user's own PC 210 or the portable terminal 220.

  In addition, a system that can compare and rank singing evaluation results with a third party by way of the server device 230 may be proposed. According to the singing evaluation system 200 configured as described above, the motivation of the singing practice of the user is led.

  The processing by the singing evaluation device 100 according to the present invention can be realized by a dedicated hardware circuit for executing the above-described procedures, or by the CPU executing a program describing the above-described procedures. When the present invention is realized by the latter, the program for operating the singing evaluation device 100 may be provided by a computer-readable recording medium such as a USB memory, a floppy (registered trademark) disk or a CD-ROM, or may be provided on the Internet. Alternatively, it may be provided online via a network such as. In this case, the program recorded on the computer-readable recording medium is usually transferred to a memory or a hard disk and stored. Further, this program may be provided, for example, as independent application software, or may be incorporated in software of the singing evaluation device 100 as one function of the device.

100 singing evaluation device,
110 CPU,
111 frequency identification unit,
112 breathing section identification unit,
113 level identification unit,
114 accompaniment data playback unit,
115 breathing section comparison unit,
116 frequency comparison unit,
117 level comparison unit,
118 output unit,
120 memories,
130 hard disk,
140 communication I / F section,
150 display,
160 operation unit,
170 voice input unit,
180 audio output unit,
190 bus,
200 singing evaluation system,
210 PC (user terminal),
220 mobile terminal (user terminal),
230 server devices,
240 networks.

Claims (12)

A singing evaluation method that evaluates the skill of the user's singing,
From the target voice data representing the target voice targeted by the user, specify the frequency of the target voice that transitions in time, from the user voice data representing the user voice that is the user's voice, the frequency of the user voice that transitions in time A frequency identification step of identifying
Based on the frequency of the target speech, the frequency have your target speech over the evenly scattered wide range identifies the breathing segment that exist innumerable frequency as target respiration interval, based on the frequency of the user voice Te, a breathing segment specifying step of specifying a breathing segment that exist innumerable frequency as a user breathing segment over a wide range scattered is evenly frequency have you to the user voice,
A breathing section comparison step of comparing the target breathing section and the user breathing section,
An output step of outputting a result compared in the breathing section comparison step. Based on the frequency of the target voice and the frequency of the user voice, at the same timing of the singing proceeding, further comprising a frequency comparison step of comparing the frequency of the target voice and the frequency of the user voice,
The singing evaluation method according to claim 1, wherein in the output step, a result compared in the frequency comparison step is also output. From the target voice data, to specify the level of the target voice that changes over time, from the user voice data, a level specifying step of specifying the level of the user voice that changes over time,
At the same timing of the singing proceeding, a level comparing step of comparing the level of the target voice and the level of the user voice,
The singing evaluation method according to claim 1, wherein in the output step, a result compared in the level comparison step is also output.   The singing evaluation method according to any one of claims 1 to 3, wherein in the output step, the result is displayed as a score on a display unit.   The singing evaluation method according to any one of claims 1 to 4, wherein in the output step, advice related to the result is displayed on a display unit.   A singing evaluation program for causing a computer to execute the singing evaluation method according to any one of claims 1 to 5. A singing evaluation device that evaluates a user's skill in singing,
From the target voice data representing the target voice targeted by the user, specify the frequency of the target voice that transitions in time, from the user voice data representing the user voice that is the user's voice, the frequency of the user voice that transitions in time A frequency specifying unit for specifying
Based on the frequency of the target speech, the frequency have your target speech over the evenly scattered wide range identifies the breathing segment that exist innumerable frequency as target respiration interval, based on the frequency of the user voice Te, breathing section identifying unit for identifying the breathing segment that exist innumerable frequency as a user breathing segment over a wide range scattered is evenly frequency have you to the user voice,
A breathing section comparison unit that compares the target breathing section and the user breathing section,
A singing evaluation device, comprising: an output unit that outputs a result compared by the breathing section comparison unit. Based on the frequency of the target voice and the frequency of the user voice, at the same timing of the singing proceeding, further comprising a frequency comparison unit that compares the frequency of the target voice and the frequency of the user voice,
The singing evaluation device according to claim 7, wherein the output unit also outputs a result compared by the frequency comparison unit. From the target voice data, to specify the level of the target voice that changes over time, from the user voice data, a level specifying unit that specifies the level of the user voice that changes over time,
At the same timing of the singing proceeding, a level comparing unit that compares the level of the target voice and the level of the user voice,
The singing evaluation device according to claim 7, wherein the output unit also outputs a result compared by the level comparison unit.   The singing evaluation device according to any one of claims 7 to 9, wherein the output unit displays a result as a score on a display unit.   The singing evaluation device according to any one of claims 7 to 10, wherein the output unit displays advice related to the result on a display unit. A user terminal that generates user voice data from a user voice that is a voice of the user and transmits the user voice data via a network;
The user voice data is received from the user terminal, the user voice data is compared with target voice data representing a target voice targeted by the user, and a result of singing evaluation is transmitted. Or a server device functioning as the singing evaluation device according to claim 1,
The singing evaluation system, wherein the user terminal receives a result of the singing evaluation from the server device and outputs the result.