JP6810676B2 - Singing evaluation device, singing evaluation program and karaoke device - Google Patents

Description

The present invention relates to a singing evaluation device, a singing evaluation program, a singing evaluation method, and a karaoke device that evaluate singing when singing along with a reproduced accompaniment sound such as karaoke.

Conventionally, some karaoke devices that allow you to enjoy singing along with the accompaniment sound have a scoring function as a singing evaluation. The scoring function in the karaoke device is generally performed by comparing the main melody information in the accompaniment information with the singing voice signal input from the microphone. Therefore, the scoring function cannot be used with a sound source that does not have main melody information such as a CD.

Patent Document 1 discloses a voice evaluation device capable of scoring (singing evaluation) even for a sound source that does not have main melody information such as a CD. In this voice evaluation device, the evaluation target pitch extracted along the time axis from the voice data input from the microphone and the plurality of sounds extracted along the time axis from the audio data including a plurality of sounds, respectively. The audio data is evaluated by comparing with the reference pitch of.

JP-A-2016-122164

According to the voice evaluation device disclosed in Patent Document 1, it is possible to perform singing evaluation even for a sound source that is not provided with a main melody (correct answer data), such as a commercially available music CD. However, in Patent Document 1, since it is necessary to extract a plurality of reference pitches, it is expected that the processing load required for singing evaluation will increase. Further, since the pitch to be evaluated is compared with the reference pitch of all sounds such as main vocals, choruses, and various musical instruments included in the audio data, it is considered that the processing load required for the comparison becomes large. In addition, the singing evaluation may be inappropriate unless it is compared with an appropriate reference pitch among a plurality of reference pitches.

The present invention takes such circumstances into consideration, and even a sound source that does not have main melody information such as a CD can perform singing evaluation with high accuracy and with a reduced processing load. It is an object of the present invention to provide a singing evaluation device, a singing evaluation program, and a karaoke device that can be used.

Therefore, the singing evaluation device according to the present invention is characterized by adopting the following configuration.
A singing pitch proximity range calculation means that calculates a singing pitch neighborhood range that is a frequency range near the pitch of the singing pitch by frequency analysis of the singing voice signal input from the microphone.
From the accompaniment sound signal including the model singing sound, the model singing voice characteristic calculation means for calculating the model singing characteristic within the singing pitch vicinity range calculated by the singing pitch vicinity range calculation means, and the model singing voice characteristic calculation means.
Singing voice characteristic calculation means that calculates singing voice characteristics by frequency analysis of singing voice signals,
It is provided with an evaluation means for evaluating the singing voice signal by comparing the singing voice characteristic of the singing voice signal calculated by the singing voice characteristic calculation means with the model singing characteristic calculated by the model singing voice characteristic calculation means . It is characterized by that.

Further, in the singing evaluation device according to the present invention,
The singing pitch vicinity range is characterized in that it has a predetermined distribution with reference to the pitch of the singing voice signal in at least one of the frequency axis direction and the time axis direction.

The singing evaluation device according to the present invention is
A singing pitch proximity range calculating means for calculating a singing pitch neighborhood range from an accompaniment sound signal accompanied by information that can identify the singing pitch neighborhood range or the singing pitch neighborhood range.
A model singing voice characteristic calculation means for calculating a model singing characteristic within a range near the singing pitch from an accompaniment sound signal including a model singing sound,
It is characterized by being provided with an evaluation means for evaluating a singing voice signal by comparing the singing voice characteristic of the singing voice signal input from a microphone and the model singing characteristic.

The karaoke device according to the present invention is
With any one of the above singing evaluation devices,
It is characterized by being provided with a reproduction means for reproducing an accompaniment sound signal including a model singing sound.

The singing evaluation program according to the present invention is
Frequency analysis of the singing voice signal input from the microphone and calculation of the singing pitch neighborhood range, which is the frequency range near the pitch of the singing pitch, and the singing pitch neighborhood calculation process.
From the accompaniment sound signal including the model singing sound, the model singing voice characteristic calculation process for calculating the model singing characteristic within the singing pitch neighborhood range calculated by the singing pitch neighborhood calculation means, and
Singing voice characteristic calculation means that calculates singing voice characteristics by frequency analysis of singing voice signals,
It is possible to execute an evaluation process that evaluates the singing voice signal by comparing the singing voice characteristic of the singing voice signal calculated by the singing voice characteristic calculation means with the model singing characteristic calculated by the model singing voice characteristic calculation means. It is characterized by the fact that.

The singing evaluation program according to the present invention is
Singing pitch neighborhood calculation processing that calculates the singing pitch neighborhood range from the accompaniment sound signal with information that can identify the singing pitch neighborhood range or the singing pitch neighborhood range,
The model singing voice characteristic calculation process that calculates the model singing characteristics within the range near the singing pitch from the accompaniment sound signal including the model singing sound, and
The feature is that the singing voice characteristic of the singing voice signal input from the microphone and the evaluation process for evaluating the singing voice signal by comparing the model singing characteristic can be executed.

According to the singing evaluation device, the singing evaluation program, and the karaoke device according to the present invention, the accompaniment sound signal is used even when singing using an accompaniment sound signal such as a CD sound source to which the main melody information is not attached. By calculating the model singing voice characteristics from, it is possible to perform singing evaluation such as scoring. Then, when calculating the model singing voice characteristic from the accompaniment sound signal, it is calculated using the range near the singing pitch of the user singing, so that it is not necessary to target the entire frequency range of the accompaniment sound signal, and the processing load is increased. While suppressing it, it becomes possible to perform highly accurate singing evaluation.

Further, the range near the singing pitch used in the singing evaluation device, the singing evaluation program, and the karaoke device according to the present invention has a predetermined distribution based on the singing pitch in the frequency axis direction. By giving a predetermined distribution to the singing pitch range in this way, it is possible to perform singing evaluation with higher accuracy by weighting the model singing sound characteristics.

Further, the range near the singing pitch used in the singing evaluation device, the singing evaluation program, and the karaoke device according to the present invention has a predetermined distribution based on the singing pitch in the time axis direction. By considering the time axis direction of the singing pitch range in this way, it is possible to perform singing evaluation with higher accuracy.

Further, according to the singing evaluation device, the singing evaluation program, and the karaoke device according to the present invention, the accompaniment sound signal is accompanied by information that can specify the singing sound height vicinity range or the singing sound height vicinity range. Even when singing using an accompaniment sound signal such as a CD sound source that does not have accurate main melody information attached, singing evaluation such as scoring is performed by calculating the model singing sound characteristics from the accompaniment sound signal. It becomes possible to do. Then, when calculating the model singing voice characteristic from the accompaniment sound signal, it is calculated using the range near the singing pitch that is attached in advance, so that it is not necessary to target the entire frequency range of the accompaniment sound signal, and the processing load. It is possible to perform highly accurate singing evaluation while suppressing the above.

The figure which shows the structure of the karaoke system of this embodiment The figure which shows various data structures used in the karaoke system of this embodiment Flow chart showing performance sound probability density calculation processing of this embodiment Flow chart showing music reproduction processing of this embodiment Flow chart showing evaluation processing of this embodiment The figure for demonstrating the singing pitch neighborhood range of this embodiment The figure for demonstrating the two-dimensional normal distribution region of the pitch probability density of this embodiment. The figure for demonstrating the model singing characteristic of this embodiment The figure for demonstrating the comparison process of this embodiment.

FIG. 1 is a diagram showing a configuration of a karaoke system of the present embodiment. The karaoke system in the present embodiment includes a karaoke device 2 (sometimes called a commander) and a remote control device 1. The karaoke device 2 and the remote controller 1 are communicated and connected so as to form a network by using the LAN 100 and the access point 130.

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

Further, the karaoke device 2 includes a video reproduction means for displaying a lyrics image and a background image on the monitor 41. The video reproduction means includes a video reproduction unit 29 that reproduces an image based on the image information, a video RAM 28 that temporarily stores the image to be reproduced, a video that superimposes a lyric telop on the reproduced video, and imparts a video effect. It is configured to include a control unit 31.

Further, in this karaoke device 2, it is possible to display various information on the touch panel monitor 33 in addition to the monitor 41 connected to the outside. The touch panel monitor 33 is configured by superimposing a display unit 35 that displays video information input from the video control unit 31 and a touch panel 34 that outputs the touch-input position to the operation processing unit 22. The touch panel monitor 33 is arranged on the front surface of the housing of the karaoke device 2, and functions as an input unit like the operation unit 21 of the karaoke device 2 or the touch panel monitor 11 of the remote controller 1. By selecting a musical piece on the touch panel monitor 33, the user can perform various operations on the karaoke device 2, such as having the karaoke device 2 make a reservation directly.

Further, the karaoke device 2 is configured to include a control unit including a CPU 30 for controlling each configuration in a centralized manner and a memory 27 for temporarily storing information necessary for executing various programs.

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

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

On the other hand, the remote controller 1 can perform a music selection process of searching for a musical piece based on an instruction from the user and transmitting reservation information to the karaoke device 2 for the song for which a playback instruction has been given. Further, the remote controller 1 can receive various information from the karaoke apparatus 2 or the host apparatus 5 connected on the Internet and execute various processes. In the present embodiment, an operation unit 17 and a touch panel monitor 11 are provided as a user interface for receiving various instructions from the user. The touch panel monitor 11 includes a display unit 11a and a touch panel 11b, displays various interfaces on the display unit 11a, and can accept touch input from the user.

Further, the remote controller 1 is for controlling the memory 14 as a storage unit for storing the database required for the music selection process, various programs, and various information generated by executing the programs, and these configurations. It is configured to be equipped with a remote control side control unit. The remote control side control unit interprets the input from the CPU 15, the video control unit 13 that forms the image to be displayed on the touch panel monitor 11, the video RAM 12 that temporarily stores the video information to be displayed, the touch panel monitor 11 or the operation unit 17. The operation processing unit 18 that transmits the information to the CPU 15 is included.

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

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

The karaoke device 2 of the present embodiment can reproduce two types of music information. One type (A type) of music information is music information including singing evaluation information for performing singing evaluation. As is conventionally known, in the singing evaluation when reproducing such music information, the singing evaluation information as the main melody information is compared with the singing voice signal input from the microphone, and the degree of matching is determined. It is possible to calculate the score value based on this.

FIG. 2A is a diagram showing a data structure of music information (A type) of the present embodiment. The music information has meta information including various information related to the music information and actual information for executing various processes such as performance and display of lyrics. The meta information includes music-related information such as a music ID, a music name, a singer name, and a genre for identifying the music information. The music-related information can be used as a search target item when the user searches for a music. The actual information of the music information includes performance information, lyrics information, background video information, and the like. The performance information is information for playing a karaoke accompaniment sound, which is composed of control information for an electronic musical instrument based on the MIDI standard, compressed audio information obtained by recording an actual performance, and the like. The lyrics information is information displayed in synchronization with the performance information for singing assistance, and may be configured to change the color of the lyrics displayed in synchronization with the performance. The singing evaluation information is information for evaluating the user's singing voice at the time of playing music, and is configured to include a melody to be sung. When performing singing evaluation during music reproduction, it is possible to calculate a scoring value or the like by comparing the singing voice input to the microphones 43a and 43b with the singing evaluation information.

The other type (B type) of music information is music information that does not include singing evaluation information, for example, music that does not have singing evaluation information such as a music recorded on a CD. Conventionally, it has been difficult to evaluate singing because the singing evaluation information is not included when reproducing such music information. In the karaoke device 2 of the present embodiment, it is possible to perform singing evaluation also for such music information.

FIG. 2B is a diagram showing a data structure of music information (B type) of the present embodiment. Similar to the music information of FIG. 2A, the music information has meta information including various information related to the music information and actual information for executing various processes such as performance and display of lyrics. Since the meta information is the same as the music information of FIG. 2 (A), the description here will be omitted. The actual information includes performance information including accompaniment sounds (corresponding to the "accompaniment sound signal" in the present invention) and video information. The performance information includes accompaniment sounds obtained by recording an actual performance, such as a commercially available CD. Further, the performance information includes not only the accompaniment sound but also the singing voice by the singer (corresponding to the "model singing sound" in the present invention). The performance information in the music information (B type) is in a state where the accompaniment sound and the singing voice are mixed. The video information includes lyrics that are displayed in synchronization with the background video and accompaniment sound. The karaoke device 2 of the present embodiment can perform singing evaluation using performance information even for music information (B type) that does not include singing evaluation information.

In this embodiment, the performance sound probability density obtained in advance based on the performance information is included in the music information. This performance sound probability density is information obtained by frequency-analyzing the performance sound information including the singing sound in addition to the accompaniment sound, and includes the pitch of the singing sound and the pitches of various musical instruments used for the accompaniment. It is information.

The music information (B type) that does not include the singing evaluation information to be directly compared, such as the main melody information, includes not only the form including the performance sound probability density as in the present embodiment but also the performance sound probability density. It may be music information that is not included. In that case, the performance sound probability density is calculated at the time of music performance processing.

FIG. 3 is a flow chart showing the performance sound probability density calculation process of the present embodiment. The performance sound probability density used in the present embodiment is information obtained by analyzing performance information (corresponding to the "accompaniment sound signal" of the present invention) including a model singing sound and an accompaniment sound, and is patent No. 3413634. It is calculated according to the pitch estimation method described in the publication. In the present embodiment, the performance information included in the music information (B type) is processed in advance and included in the music information (B type), but depending on the processing capacity of the karaoke device 2, the music is being played. , The performance sound probability density may be calculated and the singing evaluation may be performed. In that case, the music information (B type) does not include the performance sound probability density.

The performance sound probability density calculation process is started by acquiring performance information from the music information to be analyzed (S100). In the pitch estimation method described in Patent No. 3413634, the trajectory of the fundamental frequency is obtained for each melody line (singing sound) and bass line (bass sound) by passing through a BPF. However, in the present embodiment, Performance information of all bands is targeted without passing through the BPF. In order to improve the analysis accuracy, zero padding (zero padding) is performed as a preprocessing before performing frequency analysis (FFT) (S101). Then, frequency analysis (S102) is executed for the zero-padded performance information. In the present embodiment, the FFT is used as the frequency analysis method, but other frequency analysis methods can also be used.

For the frequency-analyzed performance sound information, the performance sound probability density included in the performance information is calculated by using the EM algorithm (Expectation-Maximization). The EM algorithm is executed by repeatedly applying the E step (Expectation Step, S103) and the M step (Maximization Step, S104) alternately and repeatedly. At that time, by applying a sound model having a harmonic structure of the singing sound, a highly accurate performance sound probability density is calculated for the singing sound. The calculated performance sound probability density is stored in the music information to be analyzed (S105).

In the present embodiment, the performance sound probability density calculated in this way is used to include singing evaluation information that directly indicates the pitch of the singing sound such as the main melody information, such as music information (A type). It is possible to appropriately evaluate the singing even if the music information is not provided.

Then, the music reproduction processing including the evaluation processing for singing evaluation about the karaoke apparatus 2 of this embodiment will be described. FIG. 4 is a flow chart showing the music reproduction process of the present embodiment. The karaoke device 2 reserves music based on an operation on an input unit such as the remote controller 1 or the touch panel monitor 33. FIG. 2C is a data structure of reservation information stored in the memory 27 of the karaoke device 2 based on the reservation operation. The reservation information includes a music ID for identifying the music information, a user ID indicating the reserved user, a pitch setting value based on the pitch setting at the time of reservation, and the like.

The karaoke device 2 checks the reservation table stored and managed in the memory 27, and confirms the music to be played back (S201). When there is a music to be played next (S202: Yes), the music information corresponding to the music ID in the reservation information is read out and the music is started to be played (S203). During the reproduction period of the music information, the standard evaluation process (S205) or the evaluation process (S300) for evaluating the user's singing is executed. When it is determined that the music information being played is music information (A type) including singing evaluation information (S204: Yes), the standard evaluation process (S205) is executed. This standard evaluation process (S205) is a conventional singing evaluation, and compares the singing evaluation information (main melody information) included in the music information with the singing voice signals input from the microphones 43a and 43b. , It is a process of calculating the evaluation result such as the scoring value. Since the standard evaluation process (S205) is a well-known process, detailed description thereof will be omitted here.

On the other hand, when it is determined that the music information being played is music information (B type) that does not include the singing evaluation information (S204: No), the evaluation process (S300) is executed. This evaluation process (S300) is a process that is a feature of the present embodiment, and is a process that evaluates singing based on the performance sound probability density included in the music information (B type). The details of this evaluation process (S300) will be described later. When the playback of the music is completed for both the A type and the B type (S206, S207: Yes), the evaluation result determined by the standard evaluation process (S205) or the evaluation process (S300) is displayed on the monitor 41 or the like. By doing so, the user's singing ability is notified. Then, the process returns to the beginning of the music reproduction process, and then the music to be reproduced is confirmed.

FIG. 5 is a flow chart showing the evaluation process (S300) of the present embodiment. In the evaluation process (S300), evaluation is performed based on the singing voice signal input from the microphones 43a and 43b and the performance sound probability density acquired from the music information. For the singing voice signal (S303) input from the microphones 43a and 43b, the probability density of the fundamental frequency of the singing voice signal is calculated (S304). At that time, it is determined whether or not the current time is the singing section (S305). The determination of the singing section may be made by using the singing voice signal itself, or may be determined by referring to the performance sound information or the performance sound probability density. Alternatively, it is also possible to make a determination using the progress of the lyrics information included in the music information.

When it is determined to be a singing section (S305: Yes), a two-dimensional normal distribution region is calculated for the probability density of the fundamental frequency calculated in S304 (S306). FIG. 6 is a diagram for explaining a two-dimensional normal distribution region of the pitch probability density of the present embodiment. FIG. 6A is a graph showing the probability density of the fundamental frequency, and is in a state where the probability density (probability) is given for the fundamental frequency fc at the time of analysis. In the present embodiment, the evaluation accuracy is improved by applying a predetermined distribution with the fundamental frequency fc as the center (reference). In the present embodiment, a normal distribution is applied to each of the frequency direction and the time axis direction to create a two-dimensional normal distribution region shown in FIG. 6 (B). The distribution based on the fundamental frequency fc is not limited to the two-dimensional normal distribution, and may be only in the frequency axis direction or only in the time axis direction. Further, the distribution form is not a normal distribution, and various other distribution forms may be adopted. Using the created two-dimensional normal distribution region, the model singing characteristics in the performance sound probability density are extracted, and the singing voice signal is evaluated.

As described with reference to FIG. 3, the performance sound probability density includes information such as accompaniment sound and backing chorus in addition to the singing sound required for singing evaluation. Therefore, if this performance sound probability density is used as it is for evaluation, it is considered that the evaluation accuracy is lowered. In the present embodiment, the model singing characteristic is extracted by filtering the performance sound probability density with the singing voice signal, and the model singing characteristic is used for comparison with the singing voice signal to improve the evaluation accuracy. It is said. This is because, although there are differences in the skill of the singing sound depending on the singer, if the singing is performed properly, the characteristics will be similar to the model singing characteristics, and conversely, if the singing is not performed properly, the performance will be performed. The reason is that the model singing characteristics cannot be properly extracted from the sound probability density.

In the evaluation process, the performance sound probability density of the section to be evaluated is acquired (S301), and the singing pitch vicinity range based on the fundamental frequency of the singing voice signal is extracted from the acquired singing pitch high probability density. The model singing characteristic is calculated (S302). In the present embodiment, by multiplying the performance sound probability density by the two-dimensional normal distribution region of the singing sound signal, the range near the singing pitch is extracted and the model singing characteristic is calculated at the same time. It is conceivable that the user who sings sings with an octave different from the singing pitch that should be sung. Therefore, the singing pitch neighborhood range may be extracted for each of a plurality of octaves. Alternatively, it may be extracted for each of a plurality of octaves, and the octave having a high proportion of the performance sound probability density may be extracted as a range near the singing pitch.

FIG. 7 is a diagram for explaining a range near the singing pitch of the present embodiment. FIG. 7A is a graph showing the time change of the singing pitch high probability density. FIG. 7B is a graph showing a range near the singing tail pitch with respect to the graph of FIG. 7A. The range near the singing pitch shown in FIG. 7B is a range based on the fundamental frequency of the singing user, and the singing pitch probability density outside this range is not subject to singing evaluation. Therefore, it is possible to reduce the evaluation range for the frequency and reduce the load required for the evaluation process.

FIG. 8 is a diagram for explaining the calculation of the model singing characteristics of the present embodiment. FIG. 8A shows a performance sound probability density at a certain time and a two-dimensional normal distribution region calculated from the singing voice signal. The model singing characteristic shown in FIG. 8B is calculated by multiplying the performance sound probability density by the two-dimensional distribution region.

The singing evaluation is performed by comparing the calculated model singing characteristics with the two-dimensional normal distribution region (calculating the degree of agreement) (S307). FIG. 9 is a diagram for explaining the comparison process (S307) of the present embodiment. FIG. 9A is a model singing characteristic calculated based on the performance sound information, and FIG. 9B is a two-dimensional normal distribution region calculated based on the singing voice signal. The comparison process is executed by calculating the degree of agreement between the two. The higher the degree of agreement between the two, the higher the degree of agreement, that is, the singing evaluation. In the present embodiment, the two-dimensional normal distribution region is provided in both the frequency direction and the time axis direction. Therefore, it is possible to evaluate in consideration of the time axis direction. When considering the time axis direction, the model singing characteristics are converted two-dimensionally, such as using the temporal transition for the model singing characteristics, or based on the temporal transition of the two-dimensional normal distribution region. It is preferable to convert to a one-dimensional distribution region related to the frequency axis for comparison.

The score value is calculated by integrating the comparative score values calculated in the comparison process (S307) (S308). By repeatedly executing the evaluation process (S300) during the reproduction period of the music information, the score value of the entire music is calculated. When the end of playback of the music is determined (S207: Yes), the scoring value calculated as the evaluation result of the evaluation process (S300) is displayed on the monitor 41 or the like to score the singing user as the singing ability. The value is notified.

As described above, according to the karaoke system of the present embodiment, even if the music information does not include the singing evaluation information such as the main melody information, the singing pitch is in the frequency range near the pitch of the singing voice signal in the performance information. By targeting the vicinity range as the evaluation target, it is possible to reduce the processing load and perform highly accurate singing evaluation.

In the present embodiment, the probability densities are calculated and compared for both the singing voice signal and the performance sound information, but not only the probability densities but also various indexes can be used for each.

Further, in the present embodiment, the performance sound probability density obtained by analyzing the performance information is attached to the music information (B type), but this performance sound probability density is not attached in advance, and the music reproduction process is performed. It may be calculated in. Further, the information that can specify the singing pitch vicinity range or the singing pitch vicinity range is attached to the music information in advance instead of being calculated using the singing voice signal sung by the user during the music reproduction process. You may leave it as it is. In that case, the singer prepared by the music information provider (manufacturer) sings, and the range near the singing pitch obtained from the singing voice signal is attached to the music information, or the singing voice is heard. It is conceivable to attach information that can specify the range near the singing pitch obtained from the signal to the music information.

By attaching information that can identify the singing pitch vicinity range or the singing pitch vicinity range to the music information in this way, the music information provider side (manufacturer side) is as good as a professional singer. It is possible to provide an appropriate singing pitch vicinity range by using a singer who can sing moderately without it.

Although the present invention has been described above using the karaoke system, the present invention is not limited to the karaoke system. A singing evaluation device that executes singing evaluation inside or outside the karaoke device also belongs to the category of the present invention. Further, at present, a form in which a karaoke application (program) is installed on a smartphone to perform karaoke on the smartphone, or a karaoke program executed on a game machine is well known. A singing evaluation program implemented in a karaoke program that realizes the functions of the present invention by being installed in such various information processing devices also belongs to the scope of the present invention. Furthermore, it goes without saying that the singing evaluation method also belongs to the category of the present invention.

1: Remote control device 24b: Wireless LAN communication unit 2: Karaoke device 25: Acoustic control unit 5: Host device 27: Memory 11: Touch panel monitor 28: Video RAM
11a: Display unit 29: Video reproduction unit 11b: Touch panel 30: CPU
12: Video RAM 31: Video control unit 13: Video control unit 32: Hard disk 14: Memory 33: Touch panel monitor 15: CPU 34: Touch panel 16: Wireless LAN communication unit 35: Display unit 17: Operation unit 41: Monitor 18: Operation Processing unit 42: Speaker 21: Operation unit 43a, 43b: Microphone 22: Operation processing unit 130: Access point 24a: LAN communication unit

Claims (6)

A singing pitch proximity range calculation means that calculates a singing pitch neighborhood range that is a frequency range near the pitch of the singing pitch by frequency analysis of the singing voice signal input from the microphone.
From the accompaniment sound signal including the model singing sound, the model singing voice characteristic calculation means for calculating the model singing characteristic within the singing pitch vicinity range calculated by the singing pitch vicinity range calculation means, and the model singing voice characteristic calculation means.
Singing voice characteristic calculation means that calculates singing voice characteristics by frequency analysis of singing voice signals,
It is provided with an evaluation means for evaluating the singing voice signal by comparing the singing voice characteristic of the singing voice signal calculated by the singing voice characteristic calculation means with the model singing characteristic calculated by the model singing voice characteristic calculation means . A singing evaluation device characterized by this. The singing evaluation device according to claim 1, wherein the range near the singing pitch is a predetermined distribution based on the pitch of the singing voice signal in at least one of the frequency axis direction and the time axis direction. .. A singing pitch proximity range calculating means for calculating a singing pitch neighborhood range from an accompaniment sound signal accompanied by information that can identify the singing pitch neighborhood range or the singing pitch neighborhood range.
A model singing voice characteristic calculation means for calculating a model singing characteristic within a range near the singing pitch from an accompaniment sound signal including a model singing sound,
A singing evaluation device characterized in that it is provided with an evaluation means for evaluating a singing voice signal by comparing the singing voice characteristics of a singing voice signal input from a microphone with the model singing characteristics. The singing evaluation device according to any one of claims 1 to 3,
A karaoke device equipped with a reproduction means for reproducing an accompaniment sound signal. Frequency analysis of the singing voice signal input from the microphone and calculation of the singing pitch neighborhood range, which is the frequency range near the pitch of the singing pitch, and the singing pitch neighborhood calculation process.
From the accompaniment sound signal including the model singing sound, the model singing voice characteristic calculation process for calculating the model singing characteristic within the singing pitch neighborhood range calculated by the singing pitch neighborhood calculation means, and
Singing voice characteristic calculation means that calculates singing voice characteristics by frequency analysis of singing voice signals,
It is possible to execute an evaluation process that evaluates the singing voice signal by comparing the singing voice characteristic of the singing voice signal calculated by the singing voice characteristic calculation means with the model singing characteristic calculated by the model singing voice characteristic calculation means. A singing evaluation program characterized by the fact that Singing pitch neighborhood calculation processing that calculates the singing pitch neighborhood range from the accompaniment sound signal with information that can identify the singing pitch neighborhood range or the singing pitch neighborhood range,
A model singing voice characteristic calculation process that calculates the model singing characteristics within the range near the singing pitch from the accompaniment sound signal including the model or muffling,
A singing evaluation program characterized in that it is possible to execute an evaluation process that evaluates a singing voice signal by comparing the singing voice characteristics of a singing voice signal input from a microphone with the model singing characteristics.