KR20240003561A - method and apparatus for generating subtitle - Google Patents

Abstract

A subtitle generation method performed by a subtitle generation device according to an embodiment includes forming a plurality of text groups by including text and one or more subtitle cuts including a start time and an end time, and the first subtitle cut in each text group. The start time of is the same as the start time of the text group, and the end time of the last subtitle cut in the text group is formed to be the same as the end time of the text group, and the text of the first language among the plurality of text groups Arranging the group and the text group of the second language alternately in the subtitle creation screen so that the text group of one language can be arranged continuously on a plurality of lines, and the start of the ith text group among the plurality of text groups It includes the step of sharing the end visual information with the i+1th text group.

Description

Subtitle generating apparatus and method {method and apparatus for generating subtitle}

The present invention relates to a device for generating subtitles and a method for using the device to generate subtitles.

Subtitles included in video content, etc. are composed of text and time. Text in subtitles is managed by units that can be displayed on one screen (hereinafter referred to as 'subtitle cuts'), and if there is a line break, related information can also be included. In subtitles, time information can be expressed as the start and end times of the text. To create subtitles, appropriate text is needed, and each text must be assigned appropriate visual information.

Meanwhile, machine translation refers to a technology that automatically translates a specific language into another designated language. Machine translation improves accuracy through machine learning. Machine learning also requires training data, and training data generally consists of sentence pairs of the target input and output language. Since machine translation learning is mainly done on a sentence-by-sentence basis, even during actual translation, the translation quality of the entire sentence translated at once is better than the result of the sentences being broken and translated separately, one by one.

Republic of Korea Patent Publication No. 10-2351408, registration date: January 11, 2022.

According to an embodiment, a subtitle generating device capable of effectively structuring a sentence splitting situation of N:M (where N and M are natural numbers) between the original text and the translated text that occurs in a subtitle translation situation, especially a sentence splitting situation of N≠M, and Provides a method.

The problems to be solved by the present invention are not limited to those mentioned above, and other problems to be solved that are not mentioned will be clearly understood by those skilled in the art to which the present invention pertains from the following description.

The subtitle generation method performed by the subtitle generation device according to the first aspect includes text and one or more subtitle cuts including a start time and an end time to form a plurality of text groups, and the first subtitle cut in each text group The start time of is the same as the start time of the text group, and the end time of the last subtitle cut in the text group is formed to be the same as the end time of the text group, and the text of the first language among the plurality of text groups Arranging the group and the text group of the second language alternately in the subtitle creation screen so that the text group of one language can be arranged continuously on a plurality of lines, and the start of the ith text group among the plurality of text groups It includes the step of sharing the end visual information with the i+1th text group.

A subtitle generating device according to a second aspect includes an input unit that receives a command related to subtitle generation, and a processor unit that performs processing according to a command through the input unit or processing related to automatic subtitle generation, wherein the processor unit generates text and Form multiple text groups by including one or more subtitle cuts including a start time and an end time, but the start time of the first subtitle cut within each text group is the same as the start time of the text group, and the start time of the first subtitle cut within each text group is the same as the start time of the text group. The end time of the last subtitle cut is set to be the same as the end time of the corresponding text group, and among the plurality of text groups, the text group in the first language and the text group in the second language are alternately arranged within the subtitle creation screen, but only in one language. The text groups are formed to be sequentially arranged on a plurality of lines, and the start and end time information of the ith text group among the plurality of text groups is shared with the i+1th text group.

According to a third aspect, a computer program stored in a computer-readable recording medium includes instructions for causing a processor to perform the subtitle generation method.

A computer-readable recording medium storing a computer program according to the fourth aspect includes instructions for causing the computer program to cause a processor to perform the subtitle generation method.

According to the embodiment, the usability of machine translation is improved by effectively structuring the N:M (where N and M are natural numbers) sentence splitting situation between the original text and the translated text that occurs in a subtitle translation situation, especially the N≠M sentence splitting situation. The productivity of subtitle translation can be increased by increasing the user interface (UI) and displaying it to make it look more intuitive. Additionally, the translated text generated according to the embodiment has the effect of being able to be used as training data for machine translation along with the original text without adding a separate process.

1 is a configuration diagram of a subtitle generating device according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method of generating subtitles performed by a subtitle generating device according to an embodiment of the present invention.
3 to 9 are diagrams illustrating various text groups generated by a subtitle generating device according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear with reference to the embodiments described below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to be understood by those skilled in the art. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims.

The terms used in this specification will be briefly explained, and the present invention will be described in detail.

The terms used in the present invention are general terms that are currently widely used as much as possible while considering the function in the present invention, but this may vary depending on the intention or precedent of a person working in the art, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Therefore, the terms used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than simply the name of the term.

When it is said that a part 'includes' a certain element throughout the specification, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

Additionally, the term 'unit' used in the specification refers to software or hardware components such as FPGA or ASIC, and the 'unit' performs certain roles. However, 'wealth' is not limited to software or hardware. The 'part' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Therefore, as an example, 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, procedures, Includes subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted.

1 is a configuration diagram of a subtitle generating device according to an embodiment of the present invention.

Referring to FIG. 1, the subtitle generating device 100 includes an input unit 110 and a processor unit 120, and may further include a storage unit 130 and/or an output unit 140.

The input unit 110 receives commands related to subtitle creation through a user interface, etc., and transmits the input commands to the processor unit 120.

The processor unit 120 forms a plurality of text groups by including one or more subtitle cuts including text and a start time and an end time, and the start time of the first subtitle cut in each text group is the start time of the corresponding text group. The end time of the last subtitle cut in the text group is the same as the end time of the text group, and the text group in the first language and the text group in the second language among the plurality of text groups are output to the output unit 140. ) are arranged alternately within the subtitle creation screen, so that text groups of one language can be placed continuously on multiple lines, and the start and end time information of the ith text group among the plurality of text groups is added to the i+1th text. Share with the group.

Here, the first language is the original text, and the second language is a translation corresponding to the original text, and when the processor unit 120 forms a text group in one language to be continuously arranged on a plurality of lines, the second language A subtitle cut included in a text group is automatically divided into a plurality of subtitle cuts to form a plurality of split subtitle cuts. Each of the plurality of split subtitle cuts can be placed on a different line among the plurality of lines. The start time of the subtitle cut before division can be assigned to the start time of the first divided subtitle cut, and the end time of the subtitle cut before division can be assigned to the end time of the last divided subtitle cut among a plurality of divided subtitle cuts.

The i-th text group is the first language, the i+1-th text group is the second language, and when deletion of the i+1-th text group is requested through the input unit 110, the processor unit 120 deletes the i-th text group The i+2th text group and the ith text group in the same language may be formed into one integrated group, and a translation of the integrated group may be formed in the i+3th text group in the second language.

The i-th text group is the first language, the i+1-th text group is the second language, and when deletion of the i+1-th text group is requested through the input unit 110, the processor unit 120 deletes the i-th text group The i+2th text group and the ith text group in the same language can be formed into one integrated group, and the start and end times of the integrated group can be assigned to the i+3th text group in the second language. .

A computer program programmed so that the processor unit 120 of the subtitle generating device 100 performs each step included in the subtitle generating method including the series of processes described above may be recorded in the storage unit 130. . Additionally, the storage unit 130 may store the results of processing by the processor unit 120 according to control by the processor unit 120.

The output unit 140 may output the results of processing by the processor unit 120 to the outside. For example, the output unit 140 may output a subtitle screen generated according to a processing result by the processor unit 120 through a display device, etc. Meanwhile, the input unit 110 and the output unit 140 may be implemented integrally. For example, the input unit 110 may be a touch screen implemented on a display device, and the display device and the touch screen may be provided as input/output devices.

FIG. 2 is a flowchart for explaining the subtitle generating method performed by the subtitle generating device 100 according to an embodiment of the present invention, and FIGS. 3 to 9 are flowcharts showing the subtitle generating device 100 according to an embodiment of the present invention. These are drawings illustrating various text groups created by .

Hereinafter, with reference to FIGS. 1 to 9, we will take a closer look at the subtitle generation method performed by the subtitle generating device 100 according to an embodiment of the present invention.

First, the input unit 110 of the subtitle creation device 100 receives a command related to subtitle creation through a user interface, etc., and transmits the input command to the processor unit 120.

Additionally, the processor unit 120 of the subtitle generating device 100 performs processing according to commands through the input unit 110 or processing related to automatic subtitle generation. A subtitle screen may be generated according to the result of processing by the processor unit 120, and the subtitle screen generated in this way may be output through the output unit 140 under the control of the processor unit 120. 3 to 9 illustrate various text groups included in a subtitle screen that can be output through the output unit 140. By looking at the text groups that make up this subtitle screen, the contents of the generation-related processing by the processor unit 120 can be identified. Visual information is not shown in FIGS. 3 to 9 .

The composition of the subtitle screen includes text and time information.

Additionally, if the voice and text are in the same language, the cost of creating subtitles can be reduced using voice recognition. Conversely, if the voice and text are in different languages, machine translation can be used to reduce the cost of subtitle creation. This is because it is less expensive for a person to edit subtitles automatically generated by a machine than to create them manually from scratch.

However, in the case of subtitle translation, there is a limit to the amount of characters that can be displayed on one screen, so one sentence is sometimes managed by dividing it into several cuts. In this case, to obtain better machine translation results, the machine translator must be able to know information about the beginning and end of the original sentence.

In addition, there are cases where the original sentence was a single cut of subtitles, but the translation result must be separated into multiple cuts.

In addition, it is important to increase the accuracy of machine translation in order to reduce the proportion of manual work, and the corrected translation can also be used as training data for machine translation. However, due to the above situation, there are cases where the original text and the translated text do not correspond one to one, so additional manual work is required to use it for training purposes.

In situations where segmented sentences must be grouped into one sentence for machine translation, one cut of original sentence must be expressed as multiple cuts of translation, and corrected translations must also be used for machine translation training, the subtitle creation tool can be used as an editor. It must be expressed so that it is easy to understand and use.

By effectively structuring the sentence division situation of 1:N or N:1 (where N and M are natural numbers) between the original text and the translated text that occurs in the above subtitle translation situation, we can increase the usability of machine translation and make the user interface look more intuitive. There is a need. To this end, the subtitle generating device 100 and its processor unit 120 can effectively structure the N:M sentence splitting situation between the original text and the translated text that occurs in the subtitle translation situation, especially the N≠M sentence splitting situation.

Looking first at the process that the processor unit 120 processes to generate a subtitle screen, a plurality of text groups are formed by including one or more subtitle cuts including text and start and end times (S210), and each text group is formed (S210). The start time of the first subtitle cut within the text group is the same as the start time of the text group, the end time of the last subtitle cut within the text group is the same as the end time of the text group, and the first subtitle cut among the plurality of text groups is set to the same time. The text group of the first language and the text group of the second language are arranged alternately in the subtitle creation screen of the output unit 140, and the text group of one language is formed so that it can be arranged continuously on a plurality of lines (S220), and the text group of the second language is arranged alternately. Among the text groups, the start and end time information of the i-th text group is shared with the i+1-th text group (S230).

Here, the first language is the original text, and the second language is a translation corresponding to the original text, and when the processor unit 120 forms a text group in one language to be continuously arranged on a plurality of lines, the second language One subtitle cut included in a text group can be automatically divided into multiple subtitle cuts to form multiple split subtitle cuts. Here, each of the plurality of split subtitle cuts can be placed on a different line among the plurality of lines, the start time of the subtitle cut before division is assigned to the start time of the first split subtitle cut among the plurality of split subtitle cuts, and the start time of the subtitle cut before division is assigned to the start time of the first split subtitle cut among the plurality of split subtitle cuts. The ending time of the subtitle cut before division can be assigned to the ending time of the last divided subtitle cut among the divided subtitle cuts.

Figure 3 can be said to be the basic screen for subtitle translation. Subtitle cuts are listed sequentially. Subtitle cuts have text, start time, and end time as attributes. In Figure 1, visual information is not expressed separately. Each subtitle cut belongs to a specific text group, and one text group contains one or more consecutive subtitle cuts. Accordingly, the text group may be alternately composed of a text group written in the first language, which is the original text, and a text group written in the second language, which is a translation. The text group corresponding to the translation is paired with the preceding original text group and may contain a translation of the paired original text group. The text group corresponding to the translation may also have the same start time of the first subtitle cut and the same end time of the last subtitle cut as the paired original text group.

Figure 4 shows the separation of subtitle cuts of the translated text. The line break indicated by the enter symbol corresponds to a user command to separate subtitle cuts based on the corresponding position, and the plus sign corresponds to a user command to create additional subtitle cuts to separate subtitle cuts in the translated text.

Figure 5 shows that the translated text is separated into two subtitle cuts as a result of the subtitle cut separation action of Figure 3. The arrow mark corresponds to a user command that combines separate translated subtitle cuts into one.

Translations automatically generated through machine translation may contain errors, so editing by the user is required. In some cases, the original subtitles and translated subtitles may need to be translated 1:N or N:1.

The example in Figure 5 can be viewed as corresponding to 1:N translation. This refers to a case where the original text requires one subtitle cut, but the translated text requires N subtitle cuts. In the structure shown in Figure 4, the translated text requiring N subtitle cuts is also shown to be recorded in one cut. The reason why it is okay to write a translation, which may be long, in one subtitle space is because the original text and translation are often not listed in word-by-word order, so the original dialogue and translated subtitles have no choice but to match the start and end times, and for this reason, When dividing one translation into N parts as shown above, the division position and subtitle display time boundary at that position can be set automatically. Therefore, even if the translation text is long, the user can write all the long translation text in one subtitle cut without the hassle of setting a time boundary, and when it is actually displayed, the processor unit 120 automatically separates and displays the subtitles at the appropriate division position and time. Just do it.

Another way to express 1:N translation is for the user to directly assign N translation sentences to multiple subtitle cuts. First, a new subtitle cut space is created through a mouse or keyboard action in the subtitle cut for the translation; second, some text of the existing subtitle cut is moved to the newly created subtitle cut space; and third, the end time of the existing subtitle cut is changed to the new subtitle cut. The end time of the cut can be assigned, and the end time of the existing subtitle cut and the start time of the new subtitle cut can be achieved through the process of allocating an appropriate time considering the allocated text length, etc. At this time, the divided subtitle cut belongs to the text group of the subtitle cut before division. The line break display in FIG. 4 explains a user command for separating subtitle cuts based on a specific position in the text. The plus sign in FIG. 4 explains a user command for adding a new empty subtitle cut after the corresponding translated subtitle cut. Figure 5 shows the results of the subtitle cut split action in Figure 4. The subtitle cut of text group 6 was divided into two subtitle cuts. Translations with divided subtitle cuts can be combined into one subtitle cut. The arrows in FIG. 5 illustrate user commands for combining the divided translated subtitle cuts back into one.

Figure 6 corresponds to a user command for deleting a translated subtitle cut between the original text in order to assign the translated text corresponding to two original text subtitle cuts to one translated subtitle cut.

Figure 7 illustrates that one translation was deleted as a result of the user command to delete the subtitle cut in Figure 6, and the translation immediately following it was changed to a translation result combining the previous two original texts. The plus sign corresponds to a user command to restore a translated subtitle cut deleted between two original subtitle cuts.

The line break mark and plus mark in FIG. 8 correspond to user commands for separating subtitle cuts of the translated text, as in FIG. 4.

Figure 9 shows that the translated text is separated into two subtitle cuts as a result of the subtitle cut separation action of Figure 8. As in Figure 5, the arrow indicates a user command to combine the separated translated subtitle cuts into one.

As previously exemplified through subtitle screens, when the i-th text group is the first language and the i+1-th text group is the second language, the processor unit 120 performs deletion of the i+1-th text group through the input unit ( When requested through 110), the i+2th text group and the ith text group in the same language as the ith text group are formed into one integrated group, and the i+3th text group in the second language is formed into an integrated group. A translation of can be formed.

In addition, when the i-th text group is the first language and the i+1-th text group is the second language, when deletion of the i+1-th text group is requested through the input unit 110, the i Form the i+2th text group and the ith text group in the same language as the th text group into one integrated group, and assign the start and end times of the integrated group to the i+3th text group in the second language. can do.

The example in Figure 7 can be viewed as corresponding to N:1 translation. N:1 translation refers to a case where the original text consists of N subtitle cuts, but the translation of the original text must be expressed with one subtitle cut. The minus sign in Figure 6 illustrates a user command for deleting translations between original texts to be merged. In the case of Figure 6, if subtitle cut 6 is deleted, the front and back subtitle cuts are integrated and managed as one text group because they are in the same language. After deleting subtitle cut 6 in FIG. 6, it can be seen that subtitle cut 5 and subtitle cut 7, which were text group 5 and text group 7, were integrated into text group 5 in FIG. 7. In addition, as the existing original text group is integrated, as shown in text group 6 in Figure 7, the translated text group must contain the integrated translation result of the translated text and its start must be synchronized with the start time of the integrated original text group. Changing the start time of a text group means that the start time of the first subtitle cut belonging to that text group also changes.

Meanwhile, a computer program may be implemented to include instructions for causing a processor to perform each step included in the subtitle generation method according to the above-described embodiment.

Additionally, a computer program including instructions for causing a processor to perform each step included in the subtitle generation method according to the above-described embodiment may be recorded on a computer-readable recording medium.

As explained so far, according to an embodiment of the present invention, a sentence splitting situation of N:M (where N and M are natural numbers) between the original text and the translated text that occurs in a subtitle translation situation, especially a sentence splitting situation of N≠M By effectively structuring, the usability of machine translation can be increased and the user interface (UI) can be displayed to look more intuitive, thereby increasing the productivity of subtitle translation. Additionally, the translated text generated according to the embodiment has the effect of being able to be used as training data for machine translation along with the original text without adding a separate processor.

Combinations of each step in each flowchart attached to the present invention may be performed by computer program instructions. Since these computer program instructions can be mounted on the processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, the instructions performed through the processor of the computer or other programmable data processing equipment perform the functions described in each step of the flowchart. It creates the means to carry out these tasks. These computer program instructions may also be stored on a computer-usable or computer-readable recording medium that can be directed to a computer or other programmable data processing equipment to implement a function in a particular way, so that the computer program instructions are computer-usable or computer-readable. The instructions stored in the recording medium can also produce manufactured items containing instruction means that perform the functions described in each step of the flowchart. Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a process that is executed by the computer and can be processed by the computer or other programmable data processing equipment. Instructions that perform processing equipment may also provide steps for executing the functions described in each step of the flowchart.

Additionally, each step may represent a module, segment, or portion of code containing one or more executable instructions for executing specified logical function(s). Additionally, it should be noted that in some alternative embodiments it is possible for the functions mentioned in the steps to occur out of order. For example, two steps shown in succession may in fact be performed substantially simultaneously, or the steps may sometimes be performed in reverse order depending on the corresponding function.

The above description is merely an illustrative explanation of the technical idea of the present invention, and those skilled in the art will be able to make various modifications and variations without departing from the essential quality of the present invention. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention shall be interpreted in accordance with the claims below, and all technical ideas within the scope equivalent thereto shall be construed as being included in the scope of rights of the present invention.

100: Subtitle generating device
110: input unit
120: Processor unit

Claims (10)

As a subtitle generating method performed by a subtitle generating device,
Form multiple text groups by including one or more subtitle cuts including text and start time and end time, but the start time of the first subtitle cut within each text group is the same as the start time of the text group, and the text The end time of the last subtitle cut in the group is formed to be the same as the end time of the corresponding text group,
Alternatingly arranging text groups in a first language and text groups in a second language among the plurality of text groups in a subtitle creation screen so that text groups in one language can be arranged continuously on a plurality of lines;
Comprising the step of sharing the start and end time information of the ith text group among the plurality of text groups with the i+1th text group.
How to create subtitles. According to claim 1,
The step of forming a text group in one language so that it can be continuously arranged on a plurality of lines,
The first language is the original text, and the second language is a translation corresponding to the original text,
Automatically dividing one subtitle cut included in the text group of the second language into a plurality of divided subtitle cuts to form a plurality of divided subtitle cuts, each of the plurality of divided subtitle cuts being placed on a different line among the plurality of lines,
The start time of the subtitle cut before division is assigned to the start time of the first subtitle cut among the plurality of divided subtitle cuts, and the end time of the subtitle cut before division is assigned to the end time of the last divided subtitle cut among the plurality of divided subtitle cuts. assigning
How to create subtitles. According to claim 1,
The i-th text group is the first language, the i+1-th text group is the second language,
When deletion of the i+1th text group is requested,
Forming the i+2th text group and the ith text group in the same language as the ith text group into one integrated group, and providing a translation of the integrated group to the i+3th text group in the second language. forming
How to create subtitles. According to claim 1,
The i-th text group is the first language, the i+1-th text group is the second language,
When deletion of the i+1th text group is requested,
The i+2th text group in the same language as the ith text group and the ith text group are formed into one integrated group, and the i+3th text group in the second language is added to the start time of the integrated group. Assigning the and end times
How to create subtitles. An input unit that receives commands related to subtitle creation,
A processor unit that performs processing according to commands through the input unit or processing related to automatic generation of subtitles,
The processor unit,
Form multiple text groups by including one or more subtitle cuts including text and start time and end time, but the start time of the first subtitle cut within each text group is the same as the start time of the text group, and the text The ending time of the last subtitle cut in the group is set to be the same as the ending time of the corresponding text group.
Among the plurality of text groups, text groups in the first language and text groups in the second language are alternately arranged in the subtitle creation screen, and the text groups in one language are formed to be continuously arranged on a plurality of lines,
Sharing the start and end time information of the ith text group among the plurality of text groups with the i+1th text group
Subtitle generating device. According to claim 5,
The first language is the original text, and the second language is a translation corresponding to the original text,
The processor unit,
When forming a group of texts in one language so that they can be placed consecutively on multiple lines,
Automatically dividing one subtitle cut included in the text group of the second language into a plurality of divided subtitle cuts to form a plurality of divided subtitle cuts, each of the plurality of divided subtitle cuts being placed on a different line among the plurality of lines,
The start time of the subtitle cut before division is assigned to the start time of the first subtitle cut among the plurality of divided subtitle cuts, and the end time of the subtitle cut before division is assigned to the end time of the last divided subtitle cut among the plurality of divided subtitle cuts. assigning
Subtitle generating device. According to claim 5,
The i-th text group is the first language, the i+1-th text group is the second language,
The processor unit,
When deletion of the i+1th text group is requested through the input unit,
Forming the i+2th text group and the ith text group in the same language as the ith text group into one integrated group, and providing a translation of the integrated group to the i+3th text group in the second language. forming
Subtitle generating device. According to claim 5,
The i-th text group is the first language, the i+1-th text group is the second language,
The processor unit,
When deletion of the i+1th text group is requested through the input unit,
The i+2th text group in the same language as the ith text group and the ith text group are formed into one integrated group, and the i+3th text group in the second language is added to the start time of the integrated group. Assigning the and end times
Subtitle generating device. A computer program stored on a computer-readable recording medium,
The computer program is,
A computer program comprising instructions for causing a processor to perform the subtitle generation method according to any one of claims 1 to 4. A computer-readable recording medium storing a computer program,
The computer program is,
A computer-readable recording medium including instructions for causing a processor to perform the subtitle generation method according to any one of claims 1 to 4.

Images