JP6689705B2 - Karaoke song support device, Karaoke song support program - Google Patents

Description

  The present invention relates to a karaoke song support device and a karaoke song support program.

  On the display unit of the karaoke device, an image in which the lyrics of the karaoke song are superimposed on the background video is displayed in time with the performance of the karaoke song. Since the user can sing a karaoke song while referring to the displayed lyrics, the user does not need to memorize the lyrics and can easily perform the karaoke song.

  On the other hand, it is difficult for a visually impaired user or a user who sits in a position where the display is difficult to see to refer to the lyrics displayed on the display.

  Here, Patent Document 1 discloses a karaoke system having a singing assist function for reading lyrics by utilizing bone conduction. Further, Patent Documents 2 and 3 disclose techniques relating to the reading of lyrics using voice synthesis.

JP, 2005-242057, A JP, 10-161683, A JP-A-11-133989

  However, the karaoke system of Patent Document 1 requires a special device for bone conduction. In addition, since bone conduction is used, there is a restriction on the stance of singing, which is complicated. Further, the techniques of Patent Documents 2 and 3 need to develop a program dedicated to a karaoke device, and therefore cannot be easily used in a karaoke device already installed in a karaoke store or the like. That is, it is difficult to easily sing a karaoke song with the conventional technology.

  An object of the present invention is to provide a karaoke singing support device and a karaoke singing support program that enable easy karaoke singing even when the displayed lyrics cannot be referred to.

A main invention for achieving the above-mentioned object is a photographing unit that photographs an image displayed on a display unit of a karaoke device in association with a karaoke performance, and a character recognition unit that recognizes a character string of lyrics included in the photographed image. And a character string included in the second image by comparing the character string included in the first image with the character string included in the second image captured at a timing later than the first image. A determination unit that determines whether a new character string that is not included in the first image is included in the string, and, if the new character string is included, converts the new character string into audio data. A karaoke singing support device having a voice data conversion unit and a voice output processing unit for outputting voice data corresponding to the new character string.
Other features of the present invention will become apparent from the description and drawings described below.

  According to the present invention, even if the displayed lyrics cannot be referred to, it becomes possible to easily sing a karaoke song.

It is a figure which shows the hardware structural example of the karaoke song support apparatus which concerns on 1st Embodiment. It is a figure which shows the software structural example of the karaoke song support apparatus which concerns on 1st Embodiment. It is a figure which shows the example of the data stored in the character storage part which concerns on 1st Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 1st Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 1st Embodiment. It is a flowchart which shows the operation example of the karaoke song support apparatus which concerns on 1st Embodiment. It is a figure which shows the software structural example of the karaoke song support apparatus which concerns on 2nd Embodiment. It is a figure which shows the data example memorize | stored in the audio | voice data storage part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment. It is a figure which shows the character string contained in the image image | photographed by the imaging part which concerns on 2nd Embodiment.

  In addition to the main invention described above, at least the following matters will be apparent from the description and drawings described below.

  That is, the determination unit may include a common character string included in both the first image and the second image in the character string included in the third image captured at a timing later than the second image. If it is determined that the common character string does not exist in the character strings included in the third image, the voice output processing unit determines whether the character string exists in the new character string. A karaoke singing support device that outputs corresponding audio data becomes clear. According to such a karaoke singing support device, it is possible to output the voice data in the vicinity of the timing of singing a new character string.

  In addition, the determination unit may include a common character string included in both the first image and the second image in the character string included in the third image captured at a timing later than the second image. It is determined whether or not there is a character string that is a character string and has been color-changed by a predetermined ratio or more, and the voice output processing unit is configured to change the color-changed character to the character string included in the third image. A karaoke singing support device that outputs voice data corresponding to the new character string becomes clear when it is determined that the string exists. According to such a karaoke singing support device, it is possible to output the voice data in the vicinity of the timing of singing a new character string.

  Further, the computer having a photographing unit is caused to cause the photographing unit to photograph an image displayed on the display unit of the karaoke device in association with the karaoke performance, and to recognize a character string of lyrics included in the photographed image. The character string included in the first image is compared with the character string included in the second image captured at a timing later than the first image, and the character string included in the second image is compared with the character string included in the second image. It is determined whether or not a new character string that is not included in the first image is included, and when the new character string is included, the new character string is converted into voice data, and the voice output unit is A karaoke singing support program for performing a process of outputting voice data corresponding to the new character string becomes clear. According to such a karaoke song support program, it is possible to easily perform a karaoke song even if the displayed lyrics cannot be referred to.

<First Embodiment>
The karaoke song support device 1 according to the first embodiment will be described with reference to FIGS. 1 to 5.

== Karaoke singing support device ==
(Hardware configuration)
The karaoke song support device 1 is a device for providing the user with the lyrics to be referred to when singing a karaoke song by voice. As the karaoke singing support device 1, a mobile terminal (notebook personal computer, tablet terminal, smartphone, etc.) owned by the user can be used.

  As shown in FIG. 1, the karaoke singing support device 1 includes a photographing unit 10, a control unit 20, a storage unit 30, a voice output unit 40, an operation unit 50, a display unit 60, and a communication unit 70.

  The image capturing section 10 is a configuration for capturing an image displayed on the display section of the karaoke device in association with the karaoke performance. The imaging unit 10 can directly use the imaging device, the imaging circuit, and the like included in the mobile terminal. The image displayed on the display unit is an image in which lyrics are superimposed on the background image. That is, the image includes a character string corresponding to the lyrics. Further, this image changes with the performance of karaoke (the character string also changes).

  The control unit 20 includes a CPU 20a and a memory 20b. The CPU 20a realizes various control functions by executing the operation program stored in the memory 20b. The memory 20b is a storage device that stores a program executed by the CPU 20a and temporarily stores various information when the program is executed. The storage unit 30 is a large-capacity storage device that stores various data.

  The voice output unit 40 is a speaker for outputting voice based on the voice data to the outside of the terminal, an amplifier for amplifying the voice data, and the like. Since "voice" and "voice data" have a one-to-one correspondence, they may be regarded as the same in the following description.

  When the user uses the karaoke singing support device 1 according to the present embodiment, the karaoke singing is performed while listening to the sound output from the sound output unit 40. At this time, since a karaoke performance sound or the like is emitted at the karaoke singing place, it may be difficult to hear the voice directly from the speaker. Therefore, it is preferable to listen to the voice from the voice output unit 40 via an earphone or the like.

  The operation unit 50 is a configuration for the user to input an instruction to the karaoke singing support device 1. In the mobile terminal, the display unit 60 of the touch panel type may be configured to also serve as the operation unit 50. The display unit 60 is a display for displaying an image captured by the image capturing unit 10 and a GUI for operation. The communication unit 70 provides an interface for communicating with a server (not shown).

(Software configuration)
The user downloads predetermined application software from a server (not shown) to the mobile terminal. A predetermined program (karaoke singing support program) is executed by activating this application. When the application is activated, a shooting mode for shooting the display section of the karaoke device is activated. When the user inputs a shooting start instruction through the operation unit 50, the shooting unit 10 sequentially shoots the images displayed on the display unit of the karaoke device based on the program. The image (image data) captured by the image capturing unit 10 is output to the character recognition unit 100 (described later). The timing of capturing an image may be every predetermined time or may be continuous (moving image).

  FIG. 2 is a diagram showing a software configuration example of the karaoke singing support device 1. The karaoke song support device 1 includes a character recognition unit 100, a character storage unit 200, a determination unit 300, a voice data conversion unit 400, and a voice output processing unit 500. The character storage unit 200 is configured as a part of the storage area of the storage unit 30. The character recognition unit 100, the determination unit 300, the voice data conversion unit 400, and the voice output processing unit 500 are realized by the CPU of the control unit 20 executing a program stored in the memory. The karaoke song support device 1 according to the present embodiment may include at least the character recognition unit 100, the determination unit 300, the voice data conversion unit 400, and the voice output processing unit 500.

[Character recognition part]
The character recognition unit 100 recognizes a character string of lyrics included in a captured image. Regarding character recognition, a technique related to optical character recognition (OCR) can be applied. As a specific example, the character recognition unit 200 scans one image output from the imaging unit 10 and determines whether there is a recognizable character string. Next, the character recognition unit 100 collates the character string determined to be recognizable with the reference character data registered in the storage unit 30 in advance, and specifies a specific character string. The character recognition unit 100 converts the recognized character string into text data, outputs it to the character storage unit 200 in association with the image ID corresponding to the image including the character string.

[Character storage]
The character storage unit 200 stores the character string recognized by the character recognition unit 100 in time series. FIG. 3 is an example of data stored in the character storage unit 200. Each character string (text data) is stored in time series in a table format associated with the image ID.

[Judgment part]
The determination unit 300 compares the character string included in the first image with the character string included in the second image captured at a timing later than the first image, and included in the second image. It is determined whether the character string includes a new character string that is not included in the first image. The comparison by the determination unit 300 is executed when a new image is captured. For example, it is assumed that the image capturing unit 10 captures images I1, I2, and I3 in this order. In this case, when the image I2 is captured, the determination unit 300 compares the character string included in the image I1 captured immediately before with the character string included in the image I2, and the image I3 is captured. If so, the character string included in the image I2 captured immediately before is compared with the character string included in the image I3. Further, whether or not a new character string is included can be determined based on whether or not the text data of each character string matches.

[Voice data converter]
When the second image includes a new character string that is not included in the first image, the voice data conversion unit 400 converts the new character string into voice data. A known technique can be used to convert a character string (text data) into voice data.

[Voice output processing unit]
The voice output processing unit 500 outputs voice data corresponding to a new character string. The audio data is output via the audio output unit 40. The user can grasp the lyrics to be sung next by listening to the voice based on the voice data output via the earphone or the like. In the present embodiment, the voice output processing unit 500 outputs the voice data at the timing when the voice data corresponding to the new character string is input.

(Operation of karaoke song support device)
Here, an operation example of the karaoke song support device 1 according to the present embodiment will be described with reference to FIGS. 4A to 5.

  4A and 4B are diagrams showing character strings included in an image captured by the image capturing unit 10. In the image I1 shown in FIG. 4A, the lyrics composed of the character string C1 and the character string C2 are displayed. The image I2 shown in FIG. 4B is taken at a timing later than the image I1, and the lyrics composed of the character strings C2 and C3 are displayed. The image I1 of FIG. 4A is an example of the “first image”, and the image I2 of FIG. 4B is an example of the “second image”. FIG. 5 is a flowchart showing an operation example of the karaoke song support device 1. It is assumed that the image I1 is an image displayed for the first time after the start of the karaoke performance of a certain song.

  First, the photographing unit 10 photographs the image I1 displayed on the display unit of the karaoke device (photographing the image I1. Step 10). The captured image I1 is output to the character recognition unit 100.

  The character recognition unit 100 recognizes the character strings C1 and C2 of the lyrics included in the image I1 captured in step 10 (recognition of the character strings C1 and C2, step 11). The character recognition unit 100 outputs the recognized character strings C1 and C2 to the character storage unit 200 in association with the identifier of the image I1.

  The character storage unit 200 stores the character strings C1 and C2 recognized in step 11 (storage of the character strings C1 and C2, step 12).

  The determination unit 300 reads the character strings C1 and C2 included in the image I1 from the character storage unit 200. Here, in this example, there is no image captured before the image I1. In this case, the determination unit 300 determines the character strings C1 and C2 as new character strings (determination of new character strings, step 13). The determination unit 300 outputs the character strings C1 and C2 to the voice data conversion unit 400.

  The voice data conversion unit 400 converts the new character strings C1 and C2 determined in step 13 into voice data (converts the character strings C1 and C2 into voice data, step 14). The voice data conversion unit 400 outputs the converted voice data to the voice output processing unit 500.

  The voice output processing unit 500 outputs the voice data corresponding to the character strings C1 and C2 converted in step 14 (outputs the voice data of the character strings C1 and C2, step 15).

  Next, the photographing unit 10 photographs the image I2 displayed on the display unit of the karaoke device (photographing the image I2, step 16). The captured image I2 is output to the character recognition unit 100.

  The character recognition unit 100 recognizes the character strings C2 and C3 of the lyrics included in the image I2 captured in step 16 (recognition of the character strings C2 and C3, step 17). The character recognition unit 100 outputs the recognized character strings C2 and C3 to the character storage unit 200 in association with the identifier of the image I2.

  The character storage unit 200 stores the character strings C2 and C3 recognized in step 17 (storage of character strings C2 and C3, step 18).

  When the new image I2 is captured, the determination unit 300 determines the character strings C2 and C3 (the character strings C2 and C3 stored in step 18) included in the new image I2 and the image captured immediately before. The character strings C1 and C2 included in I1 (the character strings C1 and C2 stored in step 12) are read from the character storage unit 200. Then, the determination unit 300 determines whether the character string included in the image I2 includes a new character string that is not included in the image I1 (determination of a new character string, step 19). In this example, the image I2 includes the new character string C3. In this case, the determination unit 300 outputs the character string C3 to the voice data conversion unit 400. If the new character string is not included, no special processing is performed. The determination unit 300 performs the same process for the character string included in the image I2 and the image captured at the next timing.

  The voice data conversion unit 400 converts the new character string C3 determined in step 19 into voice data (converts the character string C3 into voice data, step 20). The voice data conversion unit 400 outputs the converted voice data to the voice output processing unit 500.

  The voice output processing unit 500 outputs voice data corresponding to the new character string C3 converted in step 20 (outputs voice data of the character string C3, step 21). The karaoke singing support device 1 repeats the above-described processing until the karaoke performance of a certain music is completed.

  As described above, according to the karaoke song support device 1, the lyrics can be output as voice data. Further, by using the user's mobile terminal as the karaoke singing support device 1, the existing karaoke device can be used as it is. That is, according to the karaoke song support device 1 according to the present embodiment, even if the user cannot refer to the lyrics displayed on the display unit of the karaoke device, it becomes possible to easily perform the karaoke song.

<Second Embodiment>
The karaoke song support apparatus 1 according to the second embodiment will be described with reference to FIGS. 6 to 9C. Detailed description of the same configuration as that of the first embodiment is omitted.

  In the configuration of the first embodiment, the voice output processing unit 500 outputs the voice data at the timing when the voice data corresponding to the new character string is input from the voice data conversion unit 400. In this case, the timing when the user sings a karaoke song and the output of the voice data may overlap. For example, in the example of the first embodiment, when the voice corresponding to the character string C3 is output while the user is singing the character string C2, the singing voice of the user and the voice corresponding to the character string C3 are output. Can be heard overlapping. In this case, the user must check the voice while singing, and cannot concentrate on singing (or listening to the voice). Further, since the output voice data corresponds to a character string to be sung next, it is preferable that the output voice data be output at the timing of starting singing the character string. In the present embodiment, an example of adjusting the timing of outputting audio data will be described.

  FIG. 6 is a diagram showing a software configuration example of the karaoke singing support device 1. The karaoke singing support device 1 includes a character recognition unit 100, a character storage unit 200, a determination unit 300, a voice data conversion unit 400, a voice output processing unit 500, and a voice data storage unit 600. The character storage unit 200 and the voice data storage unit 600 are configured as part of the storage area of the storage unit 30. The character recognition unit 100, the determination unit 300, the voice data conversion unit 400, and the voice output processing unit 500 are realized by the CPU of the control unit 20 executing a program stored in the memory. The karaoke song support device 1 according to the present embodiment may include at least the character recognition unit 100, the determination unit 300, the voice data conversion unit 400, and the voice output processing unit 500.

[Voice data storage]
The voice data storage unit 600 stores the voice data converted by the voice data conversion unit 400. The voice data conversion unit 400 according to the present embodiment outputs the converted voice data to the voice data storage unit 600. The voice data storage unit 600 associates the voice data with the corresponding character string and temporarily stores the voice data. FIG. 7 is an example of data stored in the voice data storage unit 600. Each voice data (M1, M2 ...) Is chronologically stored in a table format associated with a corresponding character string.

[Judgment part]
The determination unit 300 according to the present embodiment has a function of adjusting the timing of outputting the audio data stored in the audio data storage unit 600. Two specific examples will be described below.

(Specific example 1)
As a first specific example, the determination unit 300 includes the character string included in the third image captured at a timing later than that of the second image in both the first image and the second image. Whether there is a common character string that is Specifically, the determination unit 300 identifies the character strings included in both by reading and comparing the character strings included in the first image and the character strings included in the second image. When the common character string is specified, the determination unit 300 compares the common character string with the character string of the third image and determines whether the common character string exists in the character string of the third image. To do.

  Further, when it is determined that the common character string does not exist in the character strings included in the third image, the sound output processing unit 500 outputs the sound data corresponding to the new character string.

  8A to 8C are diagrams showing character strings included in an image captured by the image capturing unit 10. In the image I1 shown in FIG. 8A, the lyrics composed of the character string C1 and the character string C2 are displayed. The image I2 shown in FIG. 8B is taken at a timing later than the image I1, and the lyrics composed of the character string C2 and the character string C3 are displayed. The image I3 shown in FIG. 8C is taken at a timing later than the image I2, and the lyrics composed of the character string C3 is displayed. The image I1 in FIG. 8A is an example of the “first image”, the image I2 in FIG. 8B is an example of the “second image”, and the image I3 in FIG. 8C is an example of the “third image”. . It is assumed that the image I1 is an image displayed for the first time after the start of the karaoke performance of a certain song.

  By the processing described in the first embodiment, each of the character strings C1 to C3 is converted into voice data. In the present embodiment, these audio data are temporarily stored in the audio data storage unit 600.

  When comparing the image I2 and the image I3, the determination unit 300 according to the present embodiment determines whether the character string included in the image I3 includes a common character string included in both the image I1 and the image I2. judge. In this example, the common character string C2 included in both the image I1 and the image I2 is not included in the image I3 (see FIG. 8C). In this case, the determination unit 300 outputs the determination result that the character string C2 is not included in the image I3 to the voice output processing unit 500.

  Here, the fact that the character string C2 included in the images I1 and I2 captured at the previous timing is not included in the image I3 captured at the later timing means that the image I3 was captured. In, it is considered that the song (karaoke performance) corresponding to the character string C2 has ended. On the other hand, since the character string C3 included in the images I2 and I3 is to be sung next to the character string C2, the character string C3 is added to the character string C3 at the time when an image that does not include the character string C2 is captured. By outputting the corresponding voice data, the user can listen to the voice at the timing of singing the character string C3.

  Therefore, the voice output processing unit 500 reads out voice data based on the new character string C3 obtained by comparing the images I1 and I2 from the voice data storage unit 600 based on the determination result from the determination unit 300, and outputs the voice data. Let

  In this way, when an image that does not include a common character string is shot, the voice data of the new character string displayed together with the common character string is output to start singing the character string. The voice data can be output in the vicinity of the timing of the operation.

(Specific example 2)
As a second specific example, the determination unit 300 includes the character string included in the third image captured at a timing later than that of the second image in both the first image and the second image. It is determined whether or not there is a common character string that has been color-changed by a predetermined ratio or more.

  The karaoke device has a function of changing the color of the character string displayed on the display unit according to the karaoke performance (the corresponding character string is displayed in white before the karaoke performance, and the corresponding character string is displayed after the karaoke performance. Is displayed in blue). “Color change” means that the color of the character string is changed by such a function. In addition, the predetermined ratio is a value for determining the timing of outputting the voice data corresponding to the character string to be sung next. The predetermined ratio can be set to any value. For example, when there are consecutive character strings A and B, if the character string A is all changed in color, then the singing of the character string B is started. Therefore, 100% (a state in which all the previous character strings are color-changed) may be set as the predetermined ratio. Alternatively, if the intervals between the character strings A and B are short, such as when the character strings A and B are continuously sung, the output timing of the audio data may be delayed after 100% color change. . Therefore, for example, 80% (80% or more of the previous character string is in a color-changed state) may be set as the predetermined ratio.

  The voice output processing unit 500 outputs the voice data corresponding to the new character string when it is determined that the character string included in the third image has a color-changed character string.

  9A to 9C are diagrams showing character strings included in an image captured by the image capturing unit 10. In the image I1 shown in FIG. 9A, the lyrics composed of the character string C1 and the character string C2 are displayed. The image I2 shown in FIG. 9B is taken at a timing later than the image I1, and the lyrics composed of the character string C2 and the character string C3 are displayed. The image I3 shown in FIG. 9C is taken at a timing later than the image I2, and the lyrics composed of the character strings C2 and C3 are displayed. The hatching in FIG. 9C indicates a character string whose color has been changed. The image I1 of FIG. 9A is an example of the “first image”, the image I2 of FIG. 9B is an example of the “second image”, and the image I3 of FIG. 9C is an example of the “third image”. . It is assumed that the image I1 is an image displayed for the first time after the start of the karaoke performance of a certain song.

  By the processing described in the first embodiment, each of the character strings C1 to C3 is converted into voice data. In the present embodiment, these audio data are temporarily stored in the audio data storage unit 600.

  When comparing the image I2 and the image I3, the determination unit 300 according to the present embodiment determines that the character string included in the image I3 is a common character string included in both the image I1 and the image I2 and has a predetermined value. It is determined whether or not there is a character string whose color has been changed in proportion to the ratio or more. In this example, the common character string C2 included in both the image I1 and the image I2 is 100% color-changed in the image I3 (see FIG. 9C). In this case, the determination unit 300 outputs to the audio output processing unit 500 a determination result that the character string C2 is color-changed at a predetermined rate or more.

  Here, the character string C2 included in the image I1 and the image I2 captured at the previous timing is color-changed in the image I3 captured at the later timing by a predetermined ratio or more, which means that the image I3 is changed. It is considered that the song (karaoke performance) corresponding to the character string C2 is completed at the time when is photographed. On the other hand, since the character string C3 included in the images I2 and I3 is to be sung next to the character string C2, the time when the color-changed image of the character string C2 is taken at a predetermined ratio or more. By outputting voice data corresponding to the character string C3, the user can listen to the voice at the timing of singing the character string C3.

  Therefore, the voice output processing unit 500 reads out voice data based on the new character string C3 obtained by comparing the images I1 and I2 from the voice data storage unit 600 based on the determination result from the determination unit 300, and outputs the voice data. Let

  In this way, when the common character string is color-changed by a predetermined ratio or more, the voice data of the new character string displayed together with the common character string is output to start singing the character string. The voice data can be output in the vicinity of the timing of the operation.

  It is also possible to supply a program to a computer using a non-transitory computer readable medium with an executable program stored therein. Examples of non-transitory computer-readable media include magnetic recording media (for example, flexible disk, magnetic tape, hard disk drive), CD-ROM (Read Only Memory), and the like.

  The above embodiment is presented as an example and does not limit the scope of the invention. The above configurations can be implemented in an appropriate combination, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. The above-described embodiments and modifications thereof are included in the invention described in the claims and equivalents thereof as well as included in the scope and the gist of the invention.

1 Karaoke singing support device 10 Imaging unit 100 Character recognition unit 300 Judgment unit 400 Voice data conversion unit 500 Voice output processing unit

Claims (4)

A shooting unit that shoots an image displayed on the display unit of the karaoke device along with the karaoke performance,
A character recognition unit that recognizes the character strings of lyrics included in the captured image,
The character string included in the first image is compared with the character string included in the second image captured at a timing later than the first image, and the character string included in the second image is compared. A determination unit that determines whether or not a new character string that is not included in the first image is included;
If the new character string is included, a voice data conversion unit that converts the new character string into voice data,
A voice output processing unit for outputting voice data corresponding to the new character string,
Karaoke singing support device having. The determination unit is a common character string included in both the first image and the second image, in the character string included in the third image captured at a timing later than the second image. To determine if
The voice output processing unit outputs voice data corresponding to the new character string when it is determined that the common character string does not exist in the character strings included in the third image. The karaoke song support device according to claim 1. The determination unit is a common character string included in both the first image and the second image, in the character string included in the third image captured at a timing later than the second image. And whether or not there is a color-changed character string at a predetermined rate or more,
The voice output processing unit outputs voice data corresponding to the new character string when it is determined that the color-changed character string exists in the character string included in the third image. The karaoke singing support device according to claim 1. For a computer equipped with a shooting unit and an audio output unit,
The image capturing unit captures an image displayed on the display unit of the karaoke device along with the karaoke performance,
Recognize the text strings of the lyrics included in the captured image,
The character string included in the first image is compared with the character string included in the second image captured at a timing later than the first image, and the character string included in the second image is compared. It is determined whether a new character string that is not included in the first image is included,
When the new character string is included, the new character string is converted to voice data,
A karaoke singing support program for performing a process of outputting voice data corresponding to the new character string via the voice output unit.