JP5122598B2 - Speech input evaluation system, control method for speech input evaluation system, and program - Google Patents

Description

  The present invention relates to a speech input evaluation system, a control method for a speech input evaluation system, and a program.

  A speech input evaluation system that evaluates speech input performed by a user in accordance with music is known. A karaoke system that evaluates a song performed by a user in accordance with accompaniment music is known (for example, Patent Document 1).

JP-A-2005-208196

  In the karaoke system as described above, the user's singing voice is compared with the standard voice, and the evaluation of the user's singing is determined. Generally, the smaller the difference between the user's singing voice and the standard voice, the higher the evaluation for the user. However, in a conventional karaoke system, a user who is not good at singing cannot obtain a high evaluation, and a user who is not good at singing may feel dissatisfied. For this reason, in the karaoke system as described above, for example, it is strongly desired to realize a function to assist a user who is not good at singing so that a relatively high evaluation can be obtained.

  The present invention has been made in view of the above problems, and its purpose is to provide a voice input evaluation system that evaluates voice input performed by a user in accordance with music. For example, the user can obtain a relatively high evaluation. An object of the present invention is to provide a speech input evaluation system, a control method for a speech input evaluation system, and a program that can be assisted.

  In order to solve the above-described problems, a speech input evaluation system according to the present invention is a speech input evaluation system for evaluating speech input performed by a user in accordance with music, and speech input means for the user to input speech. Means for acquiring the model data stored in the means for storing the model data indicating the model voice input to be performed by the user in accordance with the music, the model voice input indicated by the model data, and the voice An acquisition means for acquiring an evaluation judgment criterion that associates a comparison result condition relating to a comparison result with a voice input performed via an input means and evaluation information relating to an evaluation of the user's voice input, and the exemplary data includes A comparison means for comparing the voice input of the model shown and the voice input made via the voice input means, the comparison result of the comparison means and the evaluation Evaluation means for judging an evaluation of the user's voice input based on a disconnection criterion, and the acquisition means is based on feature information of the user's voice input via the voice input means, The evaluation criteria are changed.

  In addition, the control method of the speech input evaluation system according to the present invention is a control method of the speech input evaluation system that evaluates speech input performed by the user according to music, and the exemplary speech to be performed by the user according to the music. The step of obtaining the model data stored in the means for storing the model data indicating the input, the model voice input indicated by the model data, and the voice input unit for the user to input the voice An acquisition step of acquiring an evaluation judgment criterion obtained by associating a comparison result condition relating to a comparison result between the voice input performed and evaluation information relating to an evaluation of the user's voice input; and an exemplary voice indicated by the exemplary data A comparison step for comparing the input with the voice input made through the voice input means, and the comparison result in the comparison step and the previous An evaluation step of determining an evaluation of the user's voice input based on an evaluation determination criterion, wherein the obtaining step is based on feature information of the user's voice input via the voice input means And changing the evaluation criteria.

  The program according to the present invention is a program for causing a computer to function as a voice input evaluation system that evaluates voice input performed by a user in accordance with music, and is a model that the user should perform in accordance with the music. The means for acquiring the model data stored in the means for storing the model data indicating the voice input, the model voice input indicated by the model data, and the voice input means for the user to input the voice An acquisition means for acquiring an evaluation judgment criterion obtained by associating a comparison result condition relating to a comparison result between the voice input performed and evaluation information relating to an evaluation of the user's voice input; an exemplary voice input indicated by the exemplary data And comparison means for comparing the voice input made via the voice input means, and the comparison result of the comparison means and the evaluation The computer is functioned as an evaluation unit that determines an evaluation of the user's voice input based on a disconnection criterion, and the acquisition unit uses the user's voice feature information input via the voice input unit. The program is characterized in that the evaluation criteria are changed based on the program.

  An information storage medium according to the present invention is a computer-readable information storage medium recording the above program.

  ADVANTAGE OF THE INVENTION According to this invention, in the audio | voice input evaluation system which evaluates the audio | voice input which the user performed according to music, it becomes possible to assist so that a user can obtain comparatively high evaluation, for example.

  Moreover, in one aspect of the present invention, the acquisition unit includes the evaluation determination criterion stored in the unit configured to store the evaluation determination criterion in association with each of a plurality of feature conditions related to voice feature information. You may make it acquire the said evaluation judgment criteria matched with the said feature condition where the feature information of the said user's audio | voice input via the said audio | voice input means is satisfied.

  In one aspect of the present invention, the acquisition unit includes a unit that acquires the basic evaluation criterion stored in a unit that stores a basic evaluation criterion, and is input via the voice input unit. Further, the evaluation criterion may be acquired by changing the basic evaluation criterion based on the feature information of the user's voice.

  In one aspect of the present invention, the model data may indicate at least model voice to be input by the user in accordance with the music. The evaluation criterion is a comparison result condition regarding a comparison result between a pitch of the model voice indicated by the model data and a pitch of the voice of the user input through the voice input unit, the evaluation information, , May be information associated with each other. The comparison unit may compare the pitch of the model voice indicated by the model data with the pitch of the user's voice input through the voice input unit.

  In the aspect of the invention, the example data may indicate at least an example timing at which the user should input voice. The evaluation determination criterion associates the evaluation result with the comparison result condition regarding the comparison result between the model timing indicated by the model data and the timing when the user's voice is input via the voice input unit. It may be information. The comparison unit may compare the model timing indicated by the model data with the timing when the user's voice is input via the voice input unit.

  In the aspect of the invention, the feature information may include at least one of information related to sound volume and information related to whether or not the sound is vibrato.

  In one aspect of the present invention, the voice input evaluation system may be a karaoke system in which a user sings along with the music or a game system that executes a game in which the user performs voice input in accordance with the music. Good.

It is a figure which shows the hardware constitutions of the karaoke system (voice input evaluation system) which concerns on embodiment of this invention. It is a figure which shows an example of a karaoke screen. It is a figure for demonstrating a piano roll image. It is a figure which shows another example of a karaoke screen. It is a figure which shows an example of an evaluation criteria. It is a figure which shows another example of evaluation criteria. It is a figure which shows another example of a karaoke screen. It is a figure which shows another example of a karaoke screen. It is a figure which shows another example of evaluation criteria. It is a figure which shows another example of evaluation criteria. It is a functional block diagram of a karaoke system. It is a figure which shows an example of music data. It is a figure which shows an example of the memory content of a memory | storage part. It is a flowchart which shows an example of the process performed with a karaoke system. It is a figure which shows another example of evaluation criteria. It is a figure which shows another example of a karaoke screen.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Here, the case where this invention is applied to the karaoke system which is one aspect | mode of the audio | voice input evaluation system which evaluates the audio | voice input which the user performed according to the music is demonstrated. Below, the case where the karaoke system which concerns on embodiment of this invention is implement | achieved using a consumer game machine (stationary game machine) is demonstrated. Note that the karaoke system according to the embodiment of the present invention may be realized using, for example, a portable game machine, an arcade game machine, a mobile phone, a portable information terminal, or a personal computer. Further, the karaoke system according to the embodiment of the present invention may be realized as a karaoke-dedicated device manufactured for the purpose of providing a karaoke function.

  FIG. 1 shows a hardware configuration of a karaoke system (speech input evaluation system) according to an embodiment of the present invention. As shown in FIG. 1, the karaoke system 10 includes a consumer game machine 11, a display unit 30, a voice input unit 31, a voice output unit 32, an optical disc 33 (information storage medium), and a memory card 34 (information storage medium). .

  The display unit 30, the audio input unit 31, and the audio output unit 32 are connected to the consumer game machine 11. For example, the display unit 30 is a display device such as a liquid crystal display or a plasma display. The voice input unit 31 is for a user to input voice. For example, the voice input unit 31 is a voice input device such as a microphone, and converts the input voice into an electrical signal. Further, for example, the audio output unit 32 is a speaker or headphones provided in the display device.

  The home game machine 11 is a computer system, and includes a bus 12, a control unit 13, a main memory 14, an image processing unit 15, an audio processing unit 16, an optical disk drive 17, a memory card slot 18, a communication interface (I / F) 19, And the operation unit 20.

  The bus 12 is used for exchanging addresses and data among the units of the consumer game machine 11. The control unit 13, the main memory 14, the image processing unit 15, the sound processing unit 16, the optical disk drive 17, the memory card slot 18, the communication interface 19, and the operation unit 20 are connected by the bus 12 so that mutual data communication is possible.

  The control unit 13 includes, for example, one or a plurality of microprocessors, and executes control processing and various information processing of each unit of the consumer game machine 11 based on a program read from the optical disc 33, for example. The main memory 14 includes, for example, a RAM, and a program and data read from the optical disc 33 or the memory card 34 are written as necessary. The main memory 14 is also used for work of the control unit 13.

  The image processing unit 15 includes a VRAM, draws a screen on the VRAM based on image data sent from the control unit 13, and displays the screen on the display unit 30. The audio processing unit 16 includes a sound buffer, and outputs various audio data (music, sound effects, messages, etc.) read from the optical disk 33 or the memory card 34 to the sound buffer from the audio output unit 32. In addition, the audio processing unit 16 supplies an audio signal output from the audio input unit 31 to the control unit 13.

  The optical disk drive 17 reads programs and data recorded on the optical disk 33. Here, the optical disc 33 is used to supply the program and data to the consumer game machine 11, but any other information storage medium such as a memory card 34 may be used. Moreover, you may make it supply a program and data to the consumer game machine 11 from a remote place via data communication networks, such as the internet.

  The communication interface 19 is an interface for communication connection to a data communication network such as the Internet. The memory card slot 18 is an interface for mounting the memory card 34. The memory card 34 includes a nonvolatile memory (for example, an EEPROM) and stores various data. The karaoke system 10 may include a hard disk device (auxiliary storage device). Programs and data described as being stored in the optical disk 33 or the memory card 34 may be stored in the hard disk device.

  The operation unit 20 is for a user to perform an operation. The operation unit 20 includes a plurality of operation members. The state of each operation member of the operation unit 20 is scanned at regular intervals (for example, every 1/60 seconds), and an operation signal representing the scan result is supplied to the control unit 13. The control unit 13 determines a user operation based on the operation signal.

  In the karaoke system 10, the user sings along with the accompaniment music. The audio output unit 32 mixes and outputs the accompaniment music and the user's singing voice. Moreover, in the karaoke system 10, evaluation is given to a user's song.

  FIG. 2 shows an example of a karaoke screen displayed on the display unit 30. On the karaoke screen 40, lyrics 41 to be sung by the user are displayed. “ABCDEFGHIJKL” is displayed as lyrics 41 on the karaoke screen 40 shown in FIG.

  Also, the karaoke screen 40 displays a piano roll image 42 for guiding the user to both the timing (period) when the user should sing the lyrics 41 and the pitch (pitch) that the user should utter. The The piano roll image 42 is an image simulating a piano roll generally used as a pitch notation method.

  In the piano roll image 42, a T-axis that is a time axis and a P-axis that is an axis related to a pitch are set. In the example shown in FIG. 2, the horizontal direction of the piano roll image 42 is the T-axis direction, and the vertical direction of the piano roll image 42 is the P-axis direction.

  FIG. 3 is a diagram for explaining the piano roll image 42. The piano roll image 42 shown in FIG. 3 includes a plurality of pitch images 43a to 43w corresponding to a plurality of pitches. Hereinafter, the pitch images 43a to 43w may be collectively referred to as “pitch image 43”.

  The pitch image 43 is a rectangular image whose length in the horizontal direction (T-axis direction) is longer than that in the vertical direction (P-axis direction). The white pitch image 43 corresponds to the pitch of the piano white keyboard, and the hatched pitch image 43 corresponds to the pitch of the piano black keyboard.

  The pitch images 43a to 43w are arranged in the vertical direction (P-axis direction). The pitch image 43 corresponding to a higher pitch is displayed above the piano roll image 42. That is, the pitch image 43a displayed at the bottom in the piano roll image 42 corresponds to the lowest pitch among a plurality of pitches. The pitch image 43w displayed at the top in the piano roll image 42 corresponds to the highest pitch among a plurality of pitches.

  The piano roll image 42 is divided into five regions (first region 42a, second regions 42b and 42d, and third regions 42c and 42e) in the vertical direction. The first area 42 a is an area located at the center of the piano roll image 42. The first area 42a includes a pitch image 43l corresponding to the basic pitch, three pitch images 43m, 43n, 43o corresponding to three pitches higher than the basic pitch, and three lower pitches than the basic pitch. Pitch images 43i, 43j, and 43k corresponding to the pitches are arranged. In other words, in the first region 42a, seven pitch images 43i to 43o corresponding to seven pitches of one octave centering on the basic pitch are arranged.

  The second area 42b is an area adjacent to the upper side of the first area 42a. The third region 42c is a region adjacent to the upper side of the second region 42b. In the second area 42b, four pitch images 43p, 43q, 43r, and 43s corresponding to four pitches higher than the pitch corresponding to the pitch image 43p are arranged. In the third region 42c, four pitch images 43t, 43u, 43v, and 43w corresponding to four pitches higher than the pitch corresponding to the pitch image 43s are arranged.

  On the other hand, the second region 42d is a region adjacent to the lower side of the first region 42a. The third area 42e is an area adjacent to the lower side of the second area 42d. In the second area 42d, four pitch images 43e, 43f, 43g, and 43h corresponding to four pitches lower than the pitch corresponding to the pitch image 43i are arranged. In the third region 42e, four pitch images 43a, 43b, 43c, and 43d corresponding to four pitches lower than the pitch corresponding to the pitch image 43e are arranged.

  Note that the piano roll image 42 is different from a general piano roll in that the pitch image 43 has a non-constant width in the P-axis direction. The width in the P-axis direction of each of the pitch images 43a to 43w is set to a width corresponding to the difference between the pitch corresponding to the pitch image and the basic pitch. For example, the width in the P-axis direction of the pitch image 43s corresponding to a pitch having a relatively large difference from the basic pitch is P of the pitch image 43o corresponding to a pitch having a relatively small difference from the basic pitch. It is set smaller than the axial width.

  That is, the widths of the pitch images 43e to 43h and 43p to 43s arranged in the second regions 42b and 42d are in the P-axis direction of the pitch images 43i to 43o arranged in the first region 42a. It is narrower than the width. The pitch images 43a to 43d and 43t to 43w arranged in the third regions 42c and 42e have a width in the P-axis direction, which corresponds to the pitch images 43e to 43h and 43p arranged in the second regions 42b and 42c. It is further narrower than the width in the P-axis direction of ~ 43s. By doing so, it is possible to display the pitch image 43 corresponding to as many pitches as possible within a relatively limited screen area.

  Further, as shown in FIG. 2, a reference line 44 and a singing icon 45 are displayed on the piano roll image 42. The reference line 44 is displayed on the piano roll image 42 at a position corresponding to the current time. That is, the reference line 44 indicates the current time.

  On the other hand, the singing icon 45 is displayed on the piano roll image 42 (reference line 44) at a position corresponding to the pitch of the user's voice input via the voice input unit 31. That is, the singing icon 45 is displayed on the pitch image 43 corresponding to the pitch of the user's voice. That is, the singing icon 45 plays the role of guiding the user's voice pitch to the user.

  In the case of this embodiment, when the singing icon 45 tries to move out of the first area 42a (for example, in the case shown in FIG. 2, the pitch of the user's voice is the pitch included in the first area 42a). When the pitch does not correspond to the images 43i to 43o), the piano roll image 42 is scrolled, and the singing icon 45 is displayed on the center position in the P-axis direction in the piano roll image 42. For this reason, the singing icon 45 is always displayed in the first area 42a.

  Further, a model voice guidance image 46 is displayed on the piano roll image 42. The model voice guidance image 46 plays a role of guiding both the timing (period) at which the user should sing the lyrics 41 and the pitch (pitch) of the voice (model voice) to be uttered by the user. The display position of the model voice guidance image 46 is set to a position corresponding to both the remaining time until the timing when the user should sing the lyrics 41 and the pitch of the model voice.

  For example, the P-axis coordinate value of the display position of the model voice guidance image 46 is set to a coordinate value corresponding to the pitch of the model voice. In addition, the T-axis coordinate value of the display position of the model voice guidance image 46 is set to a coordinate value corresponding to the remaining time until the timing at which the user should sing the lyrics 41 arrives. For this reason, the display position of the model voice guidance image 46 is set so that the distance from the reference line 44 becomes shorter as the remaining time until the timing at which the user should sing the lyrics 41 arrives is shorter. . As a result, the model voice guidance image 46 moves from right to left with the passage of time and approaches the reference line 44. The model voice guidance image 46 overlaps the reference line 44 at the timing when the user should sing. For example, the head 46 a of the model voice guidance image 46 reaches the reference line 44 at the timing when the user should start singing the lyrics 41.

  FIG. 4 shows an example of the karaoke screen 40 when a predetermined time has elapsed from the time shown in FIG. In the karaoke screen 40 shown in FIG. 4, a part of the model voice guidance image 46 passes through the reference line 44. That is, FIG. 4 shows a state where the first part of the lyrics 41 is already sung.

  In the karaoke screen 40 shown in FIG. 4, the lyrics 41 include a black character portion 41 a and a white character portion 41 b. The surplus portion 41a indicates a portion where the timing to sing has already passed. That is, the black portion 41a indicates a portion that the user should have already sung. On the other hand, the white part 41b shows the part where the timing to sing will come. That is, the white character part 41b has shown the part which a user will sing from now on. The first character in the white character portion 41b corresponds to the voice to be uttered next by the user.

  The change in the color of the lyrics 41 and the movement of the model voice guidance image 46 are synchronized. For this reason, the user refers to both the lyrics 41 and the model voice guidance image 46 to determine the lyrics to be sung, the timing (period) at which the lyrics should be sung, and the pitch at which the lyrics should be sung. I can grasp it.

  Further, by referring to the singing icon 45 and the model voice guidance image 46, the pitch of the voice (model voice) to be uttered by the user matches the pitch of the voice actually uttered by the user. You can also see if you are.

  In the karaoke system 10, an evaluation is given to the user's song. For example, “EXCELLENT”, “GREAT”, “GOOD” based on the difference (Δp) between the pitch of the voice that the user should sing (model voice) and the pitch of the voice that the user actually sang. , “ALMOST”, and “BOO” are given. “EXCELLENT” is the highest evaluation, and “BOO” is the lowest evaluation. FIG. 5 is a diagram showing an example of evaluation criteria, and shows an example of the relationship between pitch deviation (Δp) and evaluation. The smaller the pitch deviation (Δp), the higher the evaluation given to the user.

  Also, for example, “EXCELLENT”, “GREAT”, “GOOD”, “ALMOST” based on the deviation (Δt) between the timing when the user should sing (exemplary timing) and the timing when the user actually sang. And an evaluation of either “BOO”. FIG. 6 is a diagram showing an example of evaluation criteria, and shows an example of the relationship between timing deviation (Δt) and evaluation. The smaller the timing shift (Δt), the higher the evaluation given to the user.

  Note that, for example, the lower of the evaluation regarding the pitch shift (Δp) and the evaluation regarding the timing shift (Δt) is the evaluation of the user's song. For example, when the evaluation regarding the pitch shift (Δp) is “GREAT” and the evaluation regarding the timing shift (Δt) is “GOOD”, the evaluation of the user's song is “GOOD”.

  By the way, the size of the singing icon 45 (in the case of the present embodiment, the radius of the singing icon 45) is a pitch shift that can obtain an evaluation equal to or higher than a predetermined evaluation (here, “GREAT”). It is set to a magnitude corresponding to the magnitude of (Δp) and timing deviation (Δt). For this reason, when the singing icon 45 and the model voice guidance image 46 overlap, the magnitudes of the pitch deviation (Δp) and the timing deviation (Δt) can be evaluated as “GREAT” or more. It is within the range that can be done. For this reason, if the user sings at a pitch and timing such that the singing icon 45 and the model voice guidance image 46 overlap each other, an evaluation of “GREAT” or higher can be obtained.

  For example, on the karaoke screen 40 shown in FIG. 4, the singing icon 45 and the model voice guidance image 46 overlap. In this case, an evaluation of “GREAT” or higher is given to the user. On the other hand, for example, in the karaoke screen 40 shown in FIG. 7, the singing icon 45 and the model voice guidance image 46 do not overlap. In this case, the user is given a lower evaluation than “GREAT”.

  As shown in FIGS. 4 and 7, the karaoke screen 40 displays a message 50 indicating the evaluation given to the user. A score 47 is displayed on the karaoke screen 40. When the evaluation to be given to the user is determined, an evaluation score corresponding to the evaluation is added to the user's score. The relationship between evaluation and evaluation points is as shown in FIGS. As shown in FIGS. 5 and 6, the higher the evaluation, the higher the evaluation score.

  Further, the combo number 48 is displayed on the karaoke screen 40. The combo number 48 is the number of times that the user has continuously obtained a relatively high evaluation (eg, EXCELLENT or “GREAT”). A gauge 49 is displayed on the karaoke screen 40. The length of the gauge 49 changes based on the evaluation given to the user. For example, when the evaluation given to the user is “EXCELLENT”, “GREAT”, or “GOOD”, the gauge 49 is extended, and the evaluation is “ALMOST” or “BOO”, which is relatively low. In some cases, the gauge 49 contracts.

  By the way, in the karaoke system 10, even if it is a user who is not good at singing, it has the function for assisting so that comparatively high evaluation can be obtained. Hereinafter, this auxiliary function will be described.

  In the karaoke system 10, the evaluation criteria are changed based on the volume of the user's singing voice. Specifically, when the volume of the user's singing voice is increased, the evaluation criterion is relaxed, and a relatively high evaluation is easily obtained. For this reason, even a user who is not good at singing can easily obtain a relatively high evaluation by singing with a loud voice.

  FIG. 8 shows an example of the karaoke screen 40 when the volume of the user's singing voice is high. When the volume of the user's singing voice is large, the size of the singing icon 45 increases as shown in FIG. As described above, the size of the singing icon 45 corresponds to the pitch deviation (Δp) and timing deviation (Δt) that can obtain an evaluation equal to or higher than “GREAT”. Therefore, in this case, even if the pitch deviation (Δp) and the timing deviation (Δt) are large to some extent, the user can obtain an evaluation of “GREAT” or higher.

  As described above, when the karaoke screen 40 as shown in FIG. 8 is displayed (that is, when the volume of the user's singing voice is high), the evaluation criterion is relaxed. FIGS. 9 and 10 show an example of evaluation criteria when the karaoke screen 40 as shown in FIG. 8 is displayed (that is, when the volume of the user's singing voice is high).

  The evaluation criteria shown in FIG. 9 are looser than the evaluation criteria shown in FIG. For example, in the evaluation criteria shown in FIG. 5, if the pitch deviation (Δp) between the model voice and the user's singing voice is equal to or greater than P1 and less than P2, the evaluation of “GREAT” is given to the user. It has come to be given. On the other hand, in the evaluation criteria shown in FIG. 9, when the pitch deviation (Δp) is equal to or greater than P1 and less than P2, “EXCELLENT”, which is higher than “GREAT”, is given to the user. It is supposed to be.

  Further, according to the evaluation criteria shown in FIG. 5, when the pitch deviation (Δp) is not less than “P2” and less than “P3”, the evaluation of “GOOD” is given to the user. . On the other hand, in the evaluation criteria shown in FIG. 9, when the pitch deviation (Δp) is equal to or greater than “P2” and less than “P3”, “GREAT” is a higher evaluation than “GOOD”. Is given to the user.

  As described above, when the volume of the user's singing voice is not large, the user cannot obtain an evaluation higher than “GREAT” unless the pitch deviation (Δp) is less than “P2”. When the sound volume increases, even if the pitch deviation (Δp) is equal to or greater than “P2”, if the pitch deviation (Δp) is less than “P3”, the user obtains an evaluation of “GREAT” or higher. be able to. That is, in the evaluation judgment standard (see FIG. 9) when the volume of the user's singing voice is high, the evaluation judgment standard (see FIG. 5) when the volume of the user's singing voice is not high is higher than “GREAT”. The pitch shift (Δp) to be satisfied by the user to obtain the evaluation is large. As a result, it is easy for the user to obtain an evaluation of “GREAT” or higher.

  Similarly, the evaluation criteria shown in FIG. 10 are looser than the evaluation criteria shown in FIG. For example, in the evaluation criteria shown in FIG. 6, the difference (Δt) between the timing when the user should sing (exemplary timing) and the timing when the user actually sings is “T1” or more and “T2”. If it is less, the evaluation of “GREAT” is given to the user. On the other hand, in the evaluation criteria shown in FIG. 10, when the timing shift (Δt) is equal to or greater than “T1” and less than “T2”, “EXCELLENT”, which is higher than “GREAT”, is determined. It is given to the user.

  Further, according to the evaluation criteria shown in FIG. 6, the evaluation of “GOOD” is given to the user when the timing shift (Δt) is “T2” or more and less than “T3”. On the other hand, in the evaluation criteria shown in FIG. 10, when the timing shift (Δt) is equal to or greater than “T2” and less than “T3”, “GREAT” that is higher than “GOOD” is determined. It is given to the user.

  As described above, when the volume of the user's singing voice is low, the user cannot obtain an evaluation of “GREAT” or higher unless the timing shift (Δt) is less than “T2”. When the volume increases, even if the timing shift (Δt) is equal to or greater than “T2”, if the timing shift (Δt) is less than “T3”, the user can obtain an evaluation of “GREAT” or higher. In other words, the evaluation criterion (see FIG. 10) when the volume of the user's singing voice is high (see FIG. 10) is greater than or equal to “GREAT” compared to the evaluation criterion (see FIG. 6) when the volume of the user's singing voice is not high. The timing deviation (Δt) that the user should satisfy in order to obtain the evaluation is large. As a result, it is easy for the user to obtain an evaluation of “GREAT” or higher.

  Hereinafter, a configuration for realizing the above functions will be described. FIG. 11 is a functional block diagram showing functions realized by the karaoke system 10. As shown in FIG. 11, the karaoke system 10 includes a storage unit 60, an audio output control unit 61, an evaluation determination criterion acquisition unit 62, a comparison unit 63, and an evaluation unit 64.

  The storage unit 60 is realized by the optical disc 33, the memory card 34, and the main memory 14, for example. The storage unit 60 may be realized by an auxiliary storage device (for example, a hard disk device) provided in a device that can exchange data with the consumer game machine 11 via a communication network. That is, all or part of the data described as being stored in the storage unit 60 may be stored in the auxiliary storage device. On the other hand, functional blocks other than the storage unit 60 are realized, for example, when the control unit 13 executes a program stored on the optical disc 33.

  The storage unit 60 stores various data. In the present embodiment, the storage unit 60 stores a plurality of music data. FIG. 12 is a diagram illustrating an example of music data corresponding to one music. As shown in FIG. 11, the music data includes accompaniment music data, lyrics data, model data, and background image data. The accompaniment music data is obtained by storing the accompaniment part of a song in a predetermined data format. The accompaniment music data is, for example, MIDI data. The lyric data is data indicating the lyrics of the music. The background image data represents an image displayed as the background of the karaoke screen 40.

  The model data is data indicating a model voice input to be performed by the user in accordance with music. That is, the model data indicates the timing (period) when the user should input the voice in accordance with the music and the voice (model voice) that the user should input in accordance with the music. Specifically, the model voice data indicates a timing (period) when the user should sing lyrics in accordance with the accompaniment music and a voice (model voice) that the user who sings along with the accompaniment music should model.

  Lyric data and model data are associated with each other. For this reason, both the timing (period) at which each part of the lyrics should be sung and the pitch at which each part of the lyrics should be sung are specified based on the lyrics data and the model data. .

  In addition, the storage unit 60 is an evaluation determination criterion for determining an evaluation of the user's voice input based on a comparison result between the model voice input indicated by the model data and the voice input performed via the voice input unit 31. Remember. The evaluation criterion is information obtained by associating the comparison result condition regarding the comparison result with the evaluation information regarding the evaluation of the user's voice input. In the case of the present embodiment, the evaluation criteria as shown in FIGS. 5, 6, 9, and 10 are stored in the storage unit 60.

  The evaluation criteria shown in FIG. 5 and FIG. 9 are the comparison result condition regarding the comparison result between the pitch of the model voice indicated by the model data and the pitch of the voice of the user input through the voice input unit 31. This is information that is associated with evaluation information. The “pitch deviation (p)” field of the evaluation criteria shown in FIGS. 5 and 9 corresponds to “comparison result condition”. The “evaluation” and “evaluation value” fields correspond to “evaluation information”.

  The evaluation criteria shown in FIGS. 6 and 10 are comparison results between the model timing indicated by the model data (the timing at which the user should input voice) and the timing at which the user's voice is input via the voice input unit 31. The comparison result condition and the evaluation information are associated with each other. The “timing deviation (t)” field of the evaluation criteria shown in FIGS. 6 and 10 corresponds to the “comparison result condition”. The “evaluation” and “evaluation value” fields correspond to “evaluation information”.

  In the case of the present embodiment, the storage unit 60 stores an evaluation criterion in association with each of a plurality of feature conditions related to voice feature information. “Speech feature information” is, for example, information related to sound volume. The “speech feature information” may be, for example, information related to the frequency component of the sound.

  FIG. 13 shows an example of the contents stored in the storage unit 60. As illustrated in FIG. 13, the storage unit 60 stores a volume condition regarding the volume (v) and an evaluation determination criterion in association with each other. In FIG. 13, “evaluation judgment standard A” is the evaluation judgment standard shown in FIGS. 5 and 6, and “evaluation judgment standard B” is the evaluation judgment standard shown in FIGS. 9 and 10. As described above, the evaluation criteria shown in FIGS. 9 and 10 are looser than the evaluation criteria shown in FIGS. Therefore, in the example shown in FIG. 13, a relatively strict evaluation criterion is associated with the volume range “v <Vr” indicating a relatively low volume (v), indicating a relatively large volume (v). A relatively loose evaluation criterion is associated with the volume range “Vr ≦ v”.

  The audio output control unit 61 outputs accompaniment music from the audio output unit 32 based on the accompaniment music data. For example, the audio output control unit 61 has a sound source, and reproduces accompaniment music based on the sound source and accompaniment music data (MIDI data). The audio output control unit 61 synthesizes the accompaniment music and the user's singing voice input via the audio input unit 31 and outputs the synthesized music from the audio output unit 32.

  The evaluation criterion acquisition unit 62 acquires an evaluation criterion. The evaluation determination criterion acquisition unit 62 acquires feature information of the user's voice input via the voice input unit 31, and changes the evaluation determination criterion based on the feature information of the user's voice. In other words, the evaluation criterion acquisition unit 62 compares the comparison result condition regarding the comparison result between the model voice input indicated by the model data and the voice input performed through the voice input unit 31, and the evaluation information regarding the evaluation of the user voice input. Is changed based on the feature information of the user's voice. As described above, the “user voice feature information” is, for example, the volume or frequency component of the user voice.

  In the case of the present embodiment, the evaluation determination criterion acquisition unit 62 selects an evaluation determination criterion associated with a volume condition that satisfies the volume (v) of the user's voice among the evaluation determination criteria stored in the storage unit 60. Obtain (see FIG. 13).

  The comparison unit 63 compares the model voice input indicated by the model data with the voice input performed via the voice input unit 31. For example, the comparison unit 63 analyzes the pitch of the user's singing voice input via the voice input unit 31 and compares the pitch of the model voice indicated by the model data with the pitch of the user's singing voice. . That is, the comparison unit 63 acquires a deviation (Δp) between the pitch of the model voice indicated by the model data and the pitch of the user's singing voice.

  Further, for example, the comparison unit 63 compares the model timing indicated by the model data (the timing at which the user should sing) with the timing at which the user's singing voice is input via the voice input unit 31. That is, the comparison unit 63 acquires a deviation (Δt) between the model timing indicated by the model data and the timing when the user's singing voice is input via the voice input unit 31.

  The evaluation unit 64 determines the evaluation for the user's voice input based on the comparison result of the comparison unit 63 and the evaluation determination criterion acquired by the evaluation determination criterion acquisition unit 62. In the case of the present embodiment, the evaluation unit 64 evaluates the deviation (Δp) between the pitch of the model voice indicated by the model data and the pitch of the user's singing voice, and the evaluation judgment acquired by the evaluation judgment reference acquisition unit 62. Based on the criteria (see FIGS. 5 and 9), the user's evaluation for singing is determined. Further, the evaluation unit 64 is acquired by the evaluation determination criterion acquisition unit 62 and the deviation (Δt) between the exemplary model timing indicated by the exemplary model data and the timing when the user's singing voice is input via the audio input unit 31. Based on the evaluation criteria (see FIGS. 6 and 10), the user's evaluation for singing is determined.

  Next, processing executed by the karaoke system 10 will be described. FIG. 14 is a flowchart mainly showing processing related to the present invention among the processing executed in the karaoke system 10. The control unit 13 executes the process shown in FIG. 14 according to the program stored in the optical disc 33. The control block 13 executes the processing shown in FIG. 14 to realize the functional block shown in FIG.

  As shown in FIG. 14, first, the control unit 13 starts displaying the karaoke screen 40 and reproducing the accompaniment music (S101). Thereafter, the control unit 13 (audio output control unit 61) synthesizes the accompaniment music and the user's singing voice input via the audio input unit 31 and outputs the synthesized music from the audio output unit 32. Further, the control unit 13 repeatedly executes the processes of steps S102 to S109 every predetermined time (for example, 1/60 seconds) until the accompaniment music is finished playing.

  First, the control unit 13 (comparison unit 63) performs comparison between the singing voice and the model voice based on the model data and the user's singing voice input via the voice input unit 31 (S102).

  In step S102, for example, the control unit 13 acquires the pitch of the model voice based on the model data. Further, the control unit 13 determines the pitch of the user's singing voice input via the voice input unit 31. Then, the control unit 13 acquires a deviation (Δp) between the pitch of the singing voice and the pitch of the model voice.

  In step S102, for example, the control unit 13 acquires a deviation (Δt) between the model timing indicated by the model data and the timing when the user's singing voice is input via the voice input unit 31. Note that the timing shift (Δt) may not be acquired for each timing, but may be acquired only for the beginning part of each part. For example, in the case of the lyrics 41 shown in FIG. 2, the deviation (Δt) between the standard timing at which “A”, which is the first character of the singing, should be uttered, and the timing at which the user actually uttered “A” is acquired. For other characters (for example, “B”, etc.), the timing shift (Δt) may not be acquired.

  After the comparison between the singing voice and the model voice is executed, the control unit 13 (evaluation criterion acquisition unit 62) analyzes the user's singing voice input via the voice input unit 31, thereby the user's singing voice. Is obtained (S103). Then, the control unit 13 (evaluation determination criterion acquisition unit 62) acquires the evaluation determination criterion associated with the volume (v) acquired in step S103 from the storage unit 60 (S104). For example, when the volume (v) is smaller than the reference volume (Vr), the evaluation determination criteria shown in FIGS. 5 and 6 are acquired. On the other hand, when the volume (v) is equal to or higher than the reference volume (Vr), the evaluation criteria shown in FIGS. 9 and 10 are acquired.

  After the evaluation determination criterion is acquired, the control unit 13 (evaluation unit 64) determines the evaluation based on the comparison result in step S102 and the evaluation determination criterion acquired in step S104 (S105). Then, the control part 13 updates the score memorize | stored in the main memory 14 based on the evaluation determined in step S105 (S106). For example, the control unit 13 adds the evaluation score associated with the evaluation to the score stored in the main memory 14.

  Thereafter, the control unit 13 updates the karaoke screen 40 (S107). In step S107, for example, processing as described below is executed.

  For example, in step S107, a process for scrolling the piano roll image 42 is executed. Specifically, first, it is determined whether or not the pitch of the user's singing voice input via the voice input unit 31 is included in the basic range. Here, the “basic range” is, for example, a range of one octave centered on the basic pitch in the piano roll image 42. For example, in the case of the piano roll image 42 shown in FIG. 2, the “basic range” refers to the first area 42 a from the pitch corresponding to the pitch image 43 i included in the first area 42 a of the piano roll image 42. This is a range up to the pitch corresponding to the pitch image 43o included.

  The case where the pitch of the user's singing voice is not included in the basic range is a case where the pitch of the user's voice is no longer the pitch corresponding to the pitch image 43 included in the first region 42a. In this case, the control unit 13 changes the basic pitch in the piano roll image 42 based on the pitch of the user's singing voice. That is, the pitch of the user's singing voice is set as the basic pitch in the piano roll image 42.

  When the basic pitch in the piano roll image 42 is changed, the piano roll image 42 is updated based on the changed basic pitch. In this case, the piano roll image 42 is scrolled as a result of the basic pitch of the piano roll image 42 increasing or decreasing.

  In step S <b> 107, the singing icon 45 is displayed based on the pitch of the user's singing voice input via the voice input unit 31. That is, the singing icon 45 is displayed on the pitch image 43 corresponding to the pitch of the user's singing voice.

  Note that the size of the singing icon 45 is set based on the volume (v) of the user's singing voice input via the voice input unit 31. When the volume (v) of the user's singing voice is lower than the reference volume (Vr), the singing icon 45 is set to a normal size (the size shown in FIG. 2). On the other hand, when the volume (v) of the user's singing voice is equal to or higher than the reference volume (Vr), the singing icon 45 is set to a size larger than the normal size (the size shown in FIG. 8).

  In step S107, the lyrics 41 and the model voice guidance image 46 are displayed based on the lyrics data and the model data. In step S107, the score 47, the combo number 48, and the gauge 49 are also updated. Further, a message 50 indicating the evaluation determined in step S107 is displayed.

  After the karaoke screen 40 is updated, the control unit 13 determines whether or not the accompaniment music has been reproduced (S108). If the accompaniment music has not been played back, the control unit 13 executes the process of step S102. On the other hand, when the reproduction of the accompaniment music is completed, the control unit 13 displays a results screen on the display unit 30 (S109). Then, this process ends.

  According to the karaoke system 10 demonstrated above, it becomes possible to change the evaluation judgment criteria for judging the evaluation with respect to a user's song based on the volume of a user's song voice, for example. For example, when the volume of the user's singing voice is relatively high, it is possible to make the evaluation judgment criteria looser than when the volume of the user's singing voice is not relatively high.

  As a result, even a user who is not good at singing can easily obtain a relatively high evaluation by singing with a relatively loud voice. That is, even a user who is not good at singing can be assisted so that a relatively high evaluation can be obtained.

  The present invention is not limited to the embodiment described above.

  (1) For example, in the embodiment described above, the evaluation judgment standard (see FIGS. 5 and 6) when the volume (v) is less than the reference volume (Vr), and the volume (v) is the reference volume (Vr). The evaluation criteria (see FIGS. 9 and 10) for the above cases are stored in the storage unit 60 in advance.

  However, for example, the storage unit 60 may store in advance only one evaluation criterion as a basic evaluation criterion. Then, the evaluation determination criterion acquisition unit 62 may generate another evaluation determination criterion based on the basic evaluation determination criterion. That is, the evaluation determination criterion acquisition unit 62 may generate another evaluation determination criterion by changing the basic evaluation determination criterion.

  In this case, the storage unit 60 may store change information indicating how to change the basic evaluation criterion in association with the sound volume condition (characteristic condition relating to audio feature information). Then, the evaluation determination criterion acquisition unit 62 performs basic evaluation determination criteria based on the change information associated with the volume condition that satisfies the volume (feature information) of the user's voice input via the voice input unit 31. It is only necessary to generate other evaluation criteria by changing.

  Specifically, for example, the storage unit 60 stores, in advance, an evaluation determination criterion (see FIGS. 5 and 6) when the volume (v) is less than the reference volume (Vr) as a basic evaluation determination criterion. Also good. Then, the evaluation criterion acquisition unit 62 changes the evaluation criterion (see FIGS. 5 and 6) when the volume (v) is less than the reference volume (Vr), so that the volume (v) becomes the reference volume (Vr). ) An evaluation criterion (see FIGS. 9 and 10) for the above case may be generated.

  In this case, for example, how is the evaluation criterion (see FIGS. 5 and 6) when the volume (v) is less than the reference volume (Vr) when the volume (v) is equal to or higher than the reference volume (Vr)? Change information indicating whether to change is stored in the storage unit 60. For example, the change information in this case includes the evaluation and evaluation values when the pitch shift (Δp) is equal to or greater than “P1” and less than “P2”, from “GREAT” and “7” to “EXCELLENT” and It shows that it changes to "10". Further, for example, the change information in this case is that the evaluation and evaluation value when the timing shift (Δt) is equal to or greater than “T1” and less than “T2” are changed from “GREAT” and “7” to “EXCELLENT”. And “10”.

  When the volume (v) of the user's singing voice input via the voice input unit 31 is equal to or higher than the reference volume (Vr), the evaluation determination criterion acquisition unit 62 determines that the volume (v) is the reference volume (Vr). By changing the evaluation criterion (see FIGS. 5 and 6) when the volume is less than the threshold based on the change information, the evaluation criterion when the volume (v) is equal to or higher than the reference volume (Vr) (FIGS. 9 and 10). Reference).

  (2) Also, for example, in the embodiment described above, the evaluation criterion is stored in association with each of the two volume conditions (volume range) (see FIG. 13). The evaluation criterion may be stored in association with each of the volume conditions (volume range).

  (3) Further, for example, the evaluation determination criterion acquisition unit 62 may change the evaluation determination criterion based on whether or not vibrato, which is a periodic frequency fluctuation of the singing, is applied to the user's singing voice. In this case, information on whether or not the vibrato is applied to the user's singing voice corresponds to “speech feature information”.

  For example, when vibrato is applied to the user's singing voice, the evaluation determination criterion acquisition unit 62 may change the evaluation determination criterion related to the pitch shift (Δp). FIG. 15 shows an example of evaluation criteria when vibrato is applied to the user's singing voice.

  The evaluation criteria shown in FIG. 15 are looser than the evaluation criteria shown in FIG. For example, in the evaluation criteria shown in FIG. 5, when the pitch deviation (Δp) between the model voice and the user's singing voice is “P1” or more and less than “P3”, “GREAT” or An evaluation of “GOOD” is given to the user. On the other hand, in the evaluation criteria shown in FIG. 15, when the pitch deviation (Δp) is equal to or greater than “P1” and less than “P3”, the evaluation is higher than “GREAT” and “GOOD”. A certain “EXCELLENT” is given to the user.

  Further, for example, according to the evaluation criterion shown in FIG. 5, when the pitch deviation (Δp) is equal to or larger than “P3” and smaller than “P4”, the evaluation of “ALMOST” is given to the user. Yes. On the other hand, in the evaluation criteria shown in FIG. 15, when the pitch shift (Δp) is equal to or larger than “P3” and smaller than “P4”, “GREAT” is higher than “ALMOST”. Is given to the user.

  When the vibrato is not applied to the user's singing voice, the user cannot obtain an evaluation of “GREAT” or higher unless the pitch deviation (Δp) is less than “P2”, but the vibrato is not included in the user's singing voice. As a result, even if the pitch deviation (Δp) is “P2” or more, if the pitch deviation (Δp) is less than “P4”, the user can obtain an evaluation of “GREAT” or more. it can. That is, in the evaluation judgment standard (see FIG. 15) when the user's singing voice is applied with vibrato (see FIG. 15), compared with the evaluation judgment standard (see FIG. 5) when the user's singing voice is not applied with vibrato. The pitch shift (Δp) to be satisfied by the user to obtain the above evaluation is large. As a result, it is easy for the user to obtain an evaluation of “GREAT” or higher.

  FIG. 16 shows an example of the karaoke screen 40 in this case. In this case, only the evaluation judgment standard related to the pitch shift (Δp) becomes loose, and the evaluation judgment standard related to the timing shift (Δt) does not loosen. Therefore, as shown in FIG. Has a shape extending in the P-axis direction.

  According to this modification (3), it is possible to change the evaluation criterion for determining the evaluation of the user's song based on whether or not the user's song voice is vibrato. This makes it possible to improve the interest of applying vibrato to the singing voice.

  (4) For example, the present invention is also applicable to a case where a user's voice input is evaluated in a game system (voice input evaluation system) in which a user performs a game operation and voice input in accordance with music. It is possible to apply. For example, the present invention can also be applied to a game system in which a user sings a song while dancing to music or a game system in which a user performs humming while dancing to music. Further, for example, the present invention can be applied to a game system in which a user performs a game in which a user sings a song while performing a game operation simulating the performance of a musical instrument (for example, a drum or a guitar) according to music. is there.

  DESCRIPTION OF SYMBOLS 10 Karaoke system, 11 Home-use game machine, 12 bus, 13 Control part, 14 Main memory, 15 Image processing part, 16 Sound processing part, 17 Optical disk drive, 18 Memory card slot, 19 Communication interface, 20 Operation part, 30 Display Part, 31 voice input part, 32 voice output part, 33 optical disc, 34 memory card, 40 karaoke screen, 41 lyrics, 42 piano roll image, 42a first area, 42b, 42d second area, 42c, 42e third area, 43a-43w Pitch image, 44 reference line, 45 singing icon, 46 model voice guidance image, 47 points, 48 combo number, 49 gauge, 50 message, 60 storage unit, 61 voice output control unit, 62 evaluation judgment criterion acquisition unit 63 Comparison part 64 Evaluation part.

Claims (9)

In a voice input evaluation system for evaluating voice input performed by a user according to music,
Voice input means for the user to input voice;
Means for acquiring the model data stored in the means for storing model data indicating a model voice input to be performed by the user in accordance with the music;
Evaluation judgment in which a comparison result condition relating to a comparison result between the voice input of the model indicated by the model data and the voice input performed through the voice input unit is associated with evaluation information related to the evaluation of the user's voice input. An acquisition means for acquiring a reference;
Comparison means for comparing the voice input of the model indicated by the model data and the voice input performed through the voice input means;
And a comparison result of the comparing means, the evaluation means and the evaluation criteria acquired by the acquisition means, based on the judges evaluated for the speech input of the user,
Including
The acquisition means includes the evaluation judgment criteria stored in the means for storing the evaluation judgment criteria in association with each of a plurality of volume ranges, and the user's input through the voice input means is stored. The evaluation judgment criteria used when judging the evaluation of the user's voice input by acquiring the evaluation judgment criteria associated with the volume range to which the volume of the voice belongs is obtained via the voice input means. can change based on the volume of the sound of the input the user,
A speech input evaluation system characterized by that. In a voice input evaluation system for evaluating voice input performed by a user according to music,
Voice input means for the user to input voice;
Means for acquiring the model data stored in the means for storing model data indicating a model voice input to be performed by the user in accordance with the music;
Evaluation judgment in which a comparison result condition relating to a comparison result between the voice input of the model indicated by the model data and the voice input performed through the voice input unit is associated with evaluation information related to the evaluation of the user's voice input. An acquisition means for acquiring a reference;
Comparison means for comparing the voice input of the model indicated by the model data and the voice input performed through the voice input means;
Evaluation means for determining an evaluation of the user's voice input based on the comparison result of the comparison means and the evaluation determination criteria acquired by the acquisition means;
Including
It said acquisition means,
Means for obtaining said basic evaluation criteria stored in means for storing basic evaluation criteria ,
Of the change information stored in the means for storing the change information indicating how to change the basic evaluation judgment criteria in association with each of a plurality of sound volume ranges , via the voice input means By acquiring the evaluation determination criterion by changing the basic evaluation determination criterion based on the change information associated with the volume range to which the sound volume of the user's voice inputted in the above belongs , Changing the evaluation criteria used when judging the evaluation of the user's voice input based on the volume of the user's voice input through the voice input means;
A speech input evaluation system characterized by that. The speech input evaluation system according to claim 1 or 2 ,
The exemplary data indicates at least exemplary speech to be input by the user in accordance with the music,
The evaluation criterion is a comparison result condition regarding a comparison result between a pitch of the model voice indicated by the model data and a pitch of the voice of the user input through the voice input unit, the evaluation information, , Is information that associates
The comparison means compares the pitch of the model voice indicated by the model data with the pitch of the user's voice input through the voice input means.
A speech input evaluation system characterized by that. The speech input evaluation system according to any one of claims 1 to 3 ,
The exemplary data indicates at least exemplary timing at which the user should input voice,
The evaluation determination criterion associates the evaluation result with the comparison result condition regarding the comparison result between the model timing indicated by the model data and the timing when the user's voice is input via the voice input unit. Information,
The comparing means compares the model timing indicated by the model data with the timing when the user's voice is input via the voice input means.
A speech input evaluation system characterized by that. The speech input evaluation system according to any one of claims 1 to 4 ,
The voice input evaluation system is a karaoke system in which a user sings according to the music or a game system that executes a game in which the user performs voice input according to the music. In a control method of a voice input evaluation system for evaluating voice input performed by a user according to music,
Obtaining the model data stored in a means for storing model data indicating a model voice input to be performed by the user according to the music;
A comparison result condition regarding a comparison result between a model voice input indicated by the model data and a voice input performed by a voice input means for the user to input a voice, and an evaluation of the user's voice input An obtaining step for obtaining an evaluation criterion obtained by associating the evaluation information;
A comparison step of comparing the voice input of the model indicated by the model data with the voice input made through the voice input means;
A comparison result in the comparing step, the evaluation step and the evaluation criteria acquired in the acquisition step, based on the judges evaluated for the speech input of the user,
Including
In the obtaining step, the user's input through the voice input unit among the evaluation judgment criteria stored in the means for storing the evaluation judgment criteria in association with each of a plurality of volume ranges. The evaluation judgment criterion used when judging the evaluation of the user's voice input by acquiring the evaluation judgment criterion associated with the volume range to which the sound volume belongs is input via the voice input means. been includes time variant may step on the basis of the volume of the sound of the user,
A control method for a speech input evaluation system. A program for causing a computer to function as an audio input evaluation system for evaluating audio input performed by a user in accordance with music,
Means for acquiring the model data stored in means for storing model data indicating a model voice input to be performed by the user in accordance with the music;
A comparison result condition regarding a comparison result between a model voice input indicated by the model data and a voice input performed by a voice input means for the user to input a voice, and an evaluation of the user's voice input An obtaining means for obtaining an evaluation judgment criterion obtained by associating the evaluation information,
Comparison means for comparing the voice input of the model indicated by the model data with the voice input made through the voice input means; and
And a comparison result of said comparing means, and the evaluation criteria obtained by the obtaining means, on the basis of the evaluation means for determining the evaluation of the voice input of the user,
It makes the computer function as,
The acquisition means includes the evaluation judgment criteria stored in the means for storing the evaluation judgment criteria in association with each of a plurality of volume ranges, and the user's input through the voice input means is stored. The evaluation judgment criteria used when judging the evaluation of the user's voice input by acquiring the evaluation judgment criteria associated with the volume range to which the volume of the voice belongs is obtained via the voice input means. can change based on the volume of the sound of the input the user,
A program characterized by that . In a control method of a voice input evaluation system for evaluating voice input performed by a user according to music,
Obtaining the model data stored in a means for storing model data indicating a model voice input to be performed by the user according to the music;
A comparison result condition regarding a comparison result between a model voice input indicated by the model data and a voice input performed by a voice input means for the user to input a voice, and an evaluation of the user's voice input An obtaining step for obtaining an evaluation criterion obtained by associating the evaluation information;
A comparison step of comparing the voice input of the model indicated by the model data with the voice input made through the voice input means;
An evaluation step of determining an evaluation of the user's voice input based on the comparison result in the comparison step and the evaluation determination criterion acquired in the acquisition step;
Including
The obtaining step includes
Obtaining the basic evaluation criteria stored in a means for storing basic evaluation criteria;
Of the change information stored in the means for storing the change information indicating how to change the basic evaluation judgment criteria in association with each of a plurality of sound volume ranges, via the voice input means By acquiring the evaluation determination criterion by changing the basic evaluation determination criterion based on the change information associated with the volume range to which the sound volume of the user's voice inputted in the above belongs, Changing the evaluation criteria used when judging the evaluation of the user's voice input based on the volume of the user's voice input through the voice input means,
A control method for a speech input evaluation system. A program for causing a computer to function as an audio input evaluation system for evaluating audio input performed by a user in accordance with music,
Means for acquiring the model data stored in means for storing model data indicating a model voice input to be performed by the user in accordance with the music;
A comparison result condition regarding a comparison result between a model voice input indicated by the model data and a voice input performed by a voice input means for the user to input a voice, and an evaluation of the user's voice input An obtaining means for obtaining an evaluation judgment criterion obtained by associating the evaluation information,
Comparison means for comparing the voice input of the model indicated by the model data with the voice input made through the voice input means; and
An evaluation unit that determines an evaluation of the user's voice input based on a comparison result of the comparison unit and the evaluation determination criterion acquired by the acquisition unit;
Function the computer as
The acquisition means includes
Means for obtaining said basic evaluation criteria stored in means for storing basic evaluation criteria,
Of the change information stored in the means for storing the change information indicating how to change the basic evaluation judgment criteria in association with each of a plurality of sound volume ranges, via the voice input means By acquiring the evaluation determination criterion by changing the basic evaluation determination criterion based on the change information associated with the volume range to which the sound volume of the user's voice inputted in the above belongs, Changing the evaluation criteria used when judging the evaluation of the user's voice input based on the volume of the user's voice input through the voice input means;
A program characterized by that.

Images