JP2000324394A - Method for automatically dividing title character text - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically divide a title text being the base of a title into presentation unit titles following a prescribed title presentation format by inserting a blank line into the appropriate space of an extracted unit title sentence when the number of characters in a final line is small, and extending the length of a presentation continuing time related with the final line. SOLUTION: When the final presentation unit title of a unit title sentence extracted from a title sentence text as necessary is a signal line, and the number of characters in the final line is small, a blank line is inserted into the appropriate space of the extracted unit title sentence. Thus, the length of a presentation continuing time related with the final line can be extended. For example, in an automatic title program production system 11, a presentation unit title preparing part 35 is provided with a function for converting the unit title sentence extracted by a unit title sentence extracting part 33 into at least one presentation unit title following a desired presentation format based on the unit title sentence extracted by the unit title sentence extracting part 33, dividable part information added to the unit title sentence, and information from a synchronization detecting device 15 or the like.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a closed caption text production system applied to a closed caption program production system for producing a closed caption program on the assumption that a substantially common digitized original is used for both announcement and subtitle. Regarding the division method, in particular, by applying the synchronization detection technology between the announcement voice and the subtitle sentence text proposed in the present invention, and the text division technology using Japanese feature analysis method, etc. The present invention relates to an automatic subtitle sentence text division method that can automatically divide sentence text into presentation unit subtitles according to a predetermined subtitle presentation format.

[0002]

2. Description of the Related Art Today, it is generally referred to as an advanced information society, but hearing impaired persons are in a situation where it is difficult to obtain information as compared with healthy persons.

That is, for example, a TV broadcast program which is widely used as an information medium is exemplified, and when the ratio of a subtitle program to all TV broadcast programs in Japan is referred to, it reaches 33 to 70% in Europe and the United States. Only 10
At present, it is extremely low at about%.

[0004]

Now, all T in Japan
The reason why the ratio of subtitle programs to V broadcast programs is lower than in Europe and the United States is mainly due to the lack of subtitle program production technology. Specifically, there is also a problem unique to Japanese, and most of the subtitle program production processes are manually performed, requiring a great deal of labor, time, and cost.

[0005] Therefore, the present inventors conducted a substantive investigation on the current production of subtitled programs in an attempt to investigate the cause of hindrance to the development of subtitled program production technology.

[0008] The left side of FIG. 8 shows a subtitle program production flow that is currently generally performed. In step S101, the subtitle program creator receives three subtitle manuscript creation materials, that is, program data in which the time code is superimposed on video, a program tape in which the time code is recorded on an audio channel, and a program script. Note that in the drawings, “time code” may be abbreviated as “TC”.

In step S103, the expert, such as a person who has broadcast experience, based on the subtitle manuscript preparation material received in step S101, (1) transcribes the summary of the program announcement, and (2) prepares the separately specified subtitle presentation. Caption presentation image according to the standard manuscript preparation procedure, (3) Start
The work of inputting the end time code is sequentially performed to create a subtitle manuscript.

In step S105, the input operator creates digitized subtitles based on the subtitle manuscript created in step S103.

In step S107, step S1
The digitized subtitles created in step 05 are previewed and corrected in the presence of the caption production manager in charge, the manuscript creator, and the input operator to make the completed subtitles.

[0010] Recently, by training a human resource called a caption operator who has been involved in both the summary transcription of program announcements and the digitization of subtitles, the improved current subtitle production flow shown on the right side of FIG. It has been implemented.

That is, in step S111, the subtitle program maker receives two subtitle manuscript creation materials, a program tape in which a time code is recorded on an audio channel, and a program script.

In step S113, the caption operator reproduces the program tape having the time code recorded on the audio channel, and clicks the mouse button at the start point of the dialog to extract the start time code from the audio channel at that point. Record. Furthermore, while listening to the dialogue and inputting it as summary electronic data, clicking the mouse button again at the dialogue point corresponding to the break point based on the subtitle manuscript creation procedure, extracting the end point time code from the audio channel at that point Record. These operations are repeated until the end of the program, and the subtitles of the entire program are digitized.

In step S117, step S1
The digitized subtitles created in step 05 are previewed and modified under the attendance of the caption production manager in charge and the caption operator to obtain completed subtitles.

In the latter improved current subtitle production flow, the caption operator uses only a program tape in which a time code is recorded on an audio channel to summarize and convert the dialogue into words and to divide it into presentation units. By clicking the mouse button at the timing of the dialog corresponding to the start point / end point of the subtitle, each time code of the audio channel is taken out and recorded, which can be said to be an effective subtitle production flow with considerably reduced labor.

The reason why a particularly large number of man-hours are required in a series of processing flows in the above-described current subtitle production flow is that steps S103 to S105 or step S11.
3. (1) Transcript of summary of program announcement, (2)
These are the work processes of subtitle presentation imaging and (3) entry of the start / end time code, and these work processes largely depend on the knowledge and experience of the skilled person.

However, among the subtitle programs currently being broadcast,
There are some programs in which an announcement manuscript is created in advance, and the manuscript is assumed to be actual broadcast subtitles with little modification. For example, when actually examining an information program with subtitles called "The Life of the Earth", it is assumed that the announcement sound and subtitle content are almost the same, and that a common manuscript is used for both the announcement and subtitles I can do it.

As described above, the announcement sound and the subtitle contents are very similar, and a substantially common manuscript is used for both the announcement and the subtitle, and when a program in which the manuscript is digitized is assumed, (1) ) Will hardly need to be transcribed. In this case, the remaining operations are (2) subtitle presentation imaging and (3) start / end time code entry. The inventors of the present invention have intensively studied to simplify each of the work steps, and as a result, have come up with a novel technology that can automate the subtitle presentation image of (2) without human intervention. It has been reached.

The present invention has been made in view of the above-mentioned circumstances, and employs a technique for detecting synchronization between speech and caption sentence text proposed in the present invention, a text segmentation technique using a Japanese character analysis technique, and the like. Accordingly, an object of the present invention is to provide an automatic subtitle text division method that can automatically divide a subtitle text serving as a base of a subtitle into presentation unit subtitles according to a predetermined subtitle presentation format.

[0019]

Means for Solving the Problems In order to solve the above-mentioned problems, the invention of claim 1 relates to a method for producing a subtitle program.
A subtitle sentence text division method used to divide at least a subtitle sentence text serving as a base of a subtitle into presentation unit subtitles according to a predetermined subtitle presentation format, wherein the subtitle sentence text requires a start from the beginning of the sentence. All of the first sentence-ending pause points and the punctuation marks having a length exceeding the first predetermined time are extracted from the character number range, and among the extracted first sentence-ending pause points, in particular, the first predetermined time The presence / absence of a second sentence end pause point having a length exceeding a second predetermined time longer than the second time is investigated and determined.
When it is determined that the sentence end pause point exists, the range from the beginning of the sentence to the second sentence end pause point that appears first from the beginning of the sentence in the required character range is extracted as a unit subtitle sentence, and this extracted The unit subtitle sentence is tentatively divided at the position of the first sentence end pause point to temporarily divide the unit subtitle sentence, and the number of characters per line is determined by a predetermined number for each of the plurality of tentatively divided lines. The number of characters in each line is sequentially determined based on whether or not the number of characters is equal to or more than a first predetermined number of characters that is smaller than the limited number of characters per line defined in the closed caption presentation format. When it is determined that there is a corresponding line that satisfies the condition of the number of characters or more, a line feed is restarted at a position immediately after the number of characters from the beginning reaches the first predetermined number of characters for each of the corresponding lines. By performing the provisional division of the unit subtitle sentence, an odd / even judgment is performed as to whether the total number of lines of the unit subtitle sentence temporarily divided into the plurality of lines is odd or even. As a result of the odd / even judgment, When it is determined that the number is an odd number, the number of characters on the last line of the provisionally divided unit subtitle sentence according to whether or not the number of characters on the last line is equal to or greater than a second predetermined number of characters less than the limited number of characters When a determination is made that the number of characters in the last line does not meet the condition of the second predetermined number of characters or more,
From the end of the sentence of the unit subtitle sentence, the presence or absence of the first sentence end pause point, punctuation point, or line feed point is checked according to this priority, and among these points, a line including a point that appears first between odd and even lines is determined. After that, a blank line is inserted between continuation lines, and the line break point is optimized by applying the division rule related to the recommended line break / page break point for the unit subtitle sentence at the line break point. By doing so, the gist is to automatically divide the subtitle sentence text into presentation subtitles in accordance with a predetermined subtitle presentation format.

According to the first aspect of the present invention, first, in the subtitle sentence text as the basis of the subtitle, the first character having a length exceeding the first predetermined time is set for the required character range starting from the beginning of the text. All the sentence-end pause points and the punctuation points are extracted, and among the extracted first sentence-end pause points, in particular, the second sentence that exceeds the second predetermined time which is longer than the first predetermined time. The presence or absence of a sentence end pause point is checked and determined. As a result of this investigation, when it is determined that the second sentence end pause point exists, the range from the beginning of the sentence to the second sentence end pause point that appears first from the beginning of the sentence in the required number of characters is unit subtitled. Extract as a sentence.

The above-described processing is the processing of extracting a unit subtitle sentence when the second sentence end pause point exists. In the present invention, the unit subtitle sentence extracted by the extraction processing is treated as one processing unit. Are sequentially executed. In this extraction processing, in extracting unit caption sentences within the required character range from caption sentence texts, the purpose is to avoid a situation where captions related to mutually different contents are mixed in a certain presentation unit caption. Therefore, it is preferable that the extracted unit subtitle sentences are a set of subtitle sentences having a common lump meaning. Therefore, in this extraction processing, the second sentence end pause point, which is a pause having a relatively long interval that can be regarded as a recommended page break, which tends to be inserted between unit subtitle sentences related to mutually different contents. By extracting the range from the beginning of the sentence to the second sentence pause point in the subtitle sentence text as a unit subtitle sentence, the unit subtitle sentence relating to the content of the block is intentionally extracted. ing.

Next, the extracted unit subtitle sentence is sequentially line-feeded at the position of the first sentence end pause point, so that the unit subtitle sentence is provisionally divided and the plurality of provisionally divided lines The number of characters per line is sequentially determined based on whether or not the number of characters per line is equal to or greater than a first predetermined number of characters that is less than the limited number of characters per line defined in a predetermined subtitle presentation format, and as a result of each line character number determination, When it is determined that there is a corresponding line whose number of hits is equal to or greater than the first predetermined number of characters, the number of characters from the beginning reaches the first predetermined number of characters for each of the corresponding lines. The unit subtitle sentence is provisionally divided by starting a new line at the position immediately after.

The above processing is the provisional division processing of unit subtitle sentences. Important points to be considered when performing the provisional division processing are that a line feed is performed at an appropriate place and that the number of characters per line is a predetermined number. Converge within the limited number of characters per line defined in the caption presentation format. Therefore, regarding the former line feed at an appropriate point, attention is paid to the first sentence end pause point, which is a pause with a certain length interval that can be regarded as a recommended line feed point, which tends to be inserted into a break in the text. While a group of unit subtitle sentences is sequentially line-feeded at the position of the first end-of-sentence pause point, the latter character convergence is limited to the case where the number of characters per line satisfies the condition of the first predetermined number of characters or more. For each line, the number of characters per line converges to an appropriate number of characters that does not exceed the limit by mechanically performing a line feed immediately after the number of characters from the beginning reaches the first predetermined number of characters. Considering this, the unit caption sentence is provisionally divided at an appropriate place.

Next, an odd / even judgment is made as to whether the total number of lines of the unit subtitle text provisionally divided into a plurality of lines is odd or even.
The purpose of performing the odd / even judgment is, for example, when a predetermined subtitle presentation format adopts a subtitle presentation format in which two lines of presentation unit subtitles are totally replaced, whether or not the final presentation unit subtitle is a single line This is the purpose of sorting.

When it is determined that the total number of lines is an odd number as a result of the odd / even determination, a second line in which the number of characters in the last line of the provisionally divided unit subtitle sentences is smaller than the limited number of characters is determined. The final line number of characters is determined based on whether or not the number of characters is equal to or more than the predetermined number of characters.As a result of the final line number of characters determination, when it is determined that the number of characters of the last line does not meet the condition of the second predetermined number of characters or more, From the end of the unit subtitle sentence, the first
Check for the presence of a pause point, a punctuation mark, or a line break at the end of the sentence according to this priority. Of these points, insert a line that includes the first point between odd and even lines, and insert a blank line between subsequent lines. I do.

The process described above is a blank line insertion process, and the purpose of performing the blank line insertion process is to promote accurate and reliable reading and understanding of subtitle presentation contents. More specifically, the case where the total number of lines in the unit subtitle sentence is an odd number and the number of characters in the last line does not meet the condition of the second predetermined number of characters or more means that the final presentation unit subtitle is a single line. Yes, and this means that the number of characters in the last line is relatively small. In this case, the presentation duration of a certain presentation unit subtitle depends on the number of subtitle characters included in it. Since the presentation duration time related to the last line is inevitably shortened, there is a possibility that the subtitle presentation content of the last line may be overlooked. In particular, in the case of a negative sentence, if the negation part is overlooked due to the characteristic of Japanese such that the negation word is placed at the end of the sentence, the original meaning may be misunderstood. Therefore, in such a case, from the end of the sentence of the unit subtitle sentence, the presence or absence of a first sentence end pause point, a period, or a line feed point is checked according to this priority, and among these points, between the odd and even lines. By inserting a blank line between the line containing the first occurrence of the point and the subsequent line, the presentation duration of the last line is intentionally lengthened to be longer than the original, so that the subtitle presentation contents of the last line As a result, it is possible to avoid inadvertently overlooking the subtitles as much as possible, thereby promoting accurate and reliable reading and comprehension of the subtitle presentation contents.

[0027] Then, by applying a division rule relating to a recommended line feed / page break for the unit subtitle sentence at the position of the line feed point, optimization of the line feed point is performed, whereby the subtitle sentence is obtained. The text is automatically divided into presentation unit subtitles according to a predetermined subtitle presentation format.

Here, the purpose of executing the optimization of the line feed point applying the division rule is that the first line feed point, which is the original line feed point, is used.
At the end of the sentence at the end of the sentence
Although the eligibility condition has already been satisfied and there is no room for optimization using this, the re-feeding point that is mechanically performed at the point immediately after the number of characters from the beginning reaches the first predetermined number of characters is However, it cannot be said that the eligibility condition of the division rule is always satisfied, and there is room for optimization by applying the rule. As a result, the automatic division of the subtitle sentence text into presentation subtitles according to a predetermined subtitle presentation format is ensured.

As described above, according to the first aspect of the present invention, by applying the text segmentation technique using the Japanese feature analysis technique proposed in the present invention, the caption sentence text serving as the , A method of automatically dividing subtitle sentence text that can be automatically divided into presentation unit subtitles according to the subtitle presentation format.

According to the first aspect of the present invention, among the unit caption sentences appropriately extracted from the caption sentence text, the final presentation unit caption is a single line, and the number of characters in the last line is relatively small. In the case of a small number, in the extracted unit subtitle sentences, the blanking line was inserted between the appropriate lines, so that the presentation duration time related to the last line was intentionally extended to be longer than the original one. As a result, it is possible to avoid inadvertently overlooking the subtitle presentation content of the last line as a result, thereby promoting accurate and reliable reading and understanding of the subtitle presentation content.

According to a second aspect of the present invention, there is provided the automatic subtitle sentence text dividing method according to the first aspect, wherein as a result of the investigation, it is determined that the second sentence end pause point does not exist. Then, in the required character range, the range from the beginning of the sentence to the last appearing first sentence pause point is extracted as a unit subtitle sentence, and the extracted unit subtitle sentence is targeted, and the temporary The gist is that the following processing including division is executed.

According to the second aspect of the present invention, as a result of the investigation, it is determined that there is no second sentence end pause point which is a pause having a relatively long interval which can be regarded as a recommended page break. When dropped, instead of the second sentence-pause point, attention is paid to the first sentence-end pause point, which is a pose having a certain length interval, which can be regarded as a recommended line feed point. Since the range up to the first sentence end pause point appearing last is extracted as a unit caption sentence, the following processing including the temporary division of the unit caption sentence is performed on the extracted unit caption sentence. Therefore, even when the second sentence end pause point does not exist, it is possible to intentionally extract a unit caption sentence related to a set of contents as much as possible.

Further, the invention according to claim 3 is the method for automatically dividing caption text according to any one of claims 1 and 2, wherein the first sentence end pause point, punctuation mark, or line feed. After inserting the point containing the first point between the odd and even lines and the blank line between subsequent points,
Further, the number of characters in the immediately preceding line of the inserted blank line is determined based on whether or not the number of characters in the immediately preceding line is equal to or greater than a second predetermined number of characters smaller than the limited number of characters per line defined in the predetermined subtitle presentation format. As a result of the line character number determination, when it is determined that the number of characters in the immediately preceding line does not meet the condition of the second predetermined number of characters or more, from the end of the unit subtitle sentence,
The presence or absence of the first sentence end pause point, punctuation mark, or line feed point is checked according to this priority, and among these points, a line containing a point that appears between the odd-even lines after the point that appears between the odd-even lines, and After this, a blank line is inserted during the subsequent continuation, and after the blank line is inserted, the processing of the immediately preceding line character number determination or lower is performed, and the result of the immediately preceding line character number determination indicates that the number of characters of the immediately preceding line is equal to or greater than the second predetermined number of characters. The point is to repeatedly execute until the condition is satisfied.

According to the third aspect of the present invention, after the blank line insertion processing, it is further determined that the number of characters in the line immediately before the inserted blank line does not satisfy the condition of the second predetermined number of characters or more. When it is dropped, the presentation duration of the previous line is intentionally lengthened to be longer than the original one, so that it is possible to avoid inadvertently overlooking the subtitle presentation contents of the previous line as much as possible. As a result, it is possible to promote accurate and reliable reading and comprehension of subtitle presentation contents.

Further, the invention according to claim 4 is based on claim 1
4. The method for automatically dividing caption text according to any one of (3) to (3), wherein a division rule regarding a recommended line break / page break related to the unit caption text is applied to the re-break point. After performing the optimization of the line feed portion, a determination is made as to whether or not there is a subtitle sentence following the extracted unit subtitle sentence. When the determination is made, the process returns to the initial processing step, and the following processing is repeated for the subsequent subtitle sentence. When it is determined that there is no subsequent subtitle sentence, the automatic division of the subtitle sentence text is performed. The point is to end the processing.

According to the fourth aspect of the present invention, the line break point is optimized by applying a division rule regarding a line break / recommended line break point regarding the unit subtitle sentence at the line break point. After that, when it is determined that there is a subtitle sentence subsequent to the extracted unit subtitle sentence, the process returns to the initial processing step, and the following processing is repeated for the subsequent subtitle sentence, while the subsequent subtitle sentence is When it is determined that the subtitle does not exist, the automatic division processing of the subtitle text is terminated. Therefore, the automatic division processing for all the subtitle sentences included in the subtitle text can be performed. .

Further, the invention according to claim 5 is the method for automatically dividing caption text according to any one of claims 1 to 4, wherein the unit caption text is targeted for the line feed point. In optimizing the line feed breaks by applying the division rules related to the recommended line breaks and page breaks in the sentence, the recommended line breaks and page breaks defined in the division rules are placed after the punctuation marks and after the punctuation marks. , Between phrases, and between morpheme parts of speech, one or more of the following combinations are included.
The gist is that the application is preferentially performed from the head of the description order.

According to the fifth aspect of the present invention, the line break point is optimized by applying a division rule relating to a recommended line break / page break point for the unit subtitle sentence at the line break point. In doing so, the recommended line breaks and page breaks defined by the division rule are after the period, after the punctuation,
One or more combinations between clauses and between morphemes and part-of-speech are included. In applying the division rule, the division rule is applied preferentially from the head of the description order. Thus, the automatic division of the subtitle sentence text optimized with high accuracy can be realized.

Further, the invention according to claim 6 is the method for automatically dividing caption text according to any one of claims 1 to 5, wherein the caption text is defined by the predetermined caption presentation format. The gist is that the limited number of characters N is 15 characters, and the first predetermined number of characters is 12 (= N−3) characters.

According to the sixth aspect of the present invention, the limited number of characters N per line defined in the predetermined subtitle presentation format is 15
Characters, and the first predetermined number of characters is 12
(= N-3) characters, so, for example,
When a standard caption presentation format in which the limit number of characters per line is 15 characters is adopted, the number of caption characters per line included in each presentation unit subtitle line converges to a range of 12 to 15 characters. It is possible to realize automatic division of a caption sentence text having a good appearance at the time of caption presentation.

According to a seventh aspect of the present invention, there is provided the automatic subtitle sentence text dividing method according to any one of the first to sixth aspects, wherein the method comprises the steps of: The limited number of characters N is 15 characters, and at this time, the gist is that the second predetermined number of characters is 8 (= N / 2; rounded up to the decimal point).

According to the seventh aspect of the present invention, the limited number of characters N per line defined in the predetermined subtitle presentation format is 15
Characters, and the second predetermined number of characters is 8 (=
N / 2; however, rounded up after the decimal point), so, for example, the limit number of characters per line is 1
If the standard subtitle presentation format of 5 characters is adopted, 1
The number of characters that are considered to have a small number of subtitle characters per line is 7
The threshold number of characters is set, for example, assuming that the length of one oversight operation time in which the user is looking away from the subtitle is about 0.5 to 2 seconds, and the presentation speed of the subtitle is 200
When it is assumed that characters / minute, the maximum value of 2 seconds, which is the maximum value of the oversight operation time, corresponds to about 7 characters, and from this, there is a possibility that a single oversight operation may miss 7 subtitle characters. From the verification results, it can be said that the number of characters is extremely reasonable, and as a result that can be expected at a high level as effective as possible to avoid inadvertently overlooking the subtitle presentation content of the relevant line, accurate and reliable It is possible to drastically promote reading and comprehension of the contents of the subtitle presentation.

[0043]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of a method for automatically dividing caption text according to the present invention will be described in detail with reference to the drawings.

FIG. 1 is a functional block diagram of an automatic subtitle program production system embodying the automatic subtitle text division method according to the present invention. FIG. 2 is a flowchart showing a subtitle text division procedure. FIG. 4 is a diagram showing a state where a unit caption sentence is provisionally divided at an appropriate place, FIG. 4 is a view showing a state where a blank line is inserted at an appropriate place in the unit caption sentence, and FIG.
6 is a diagram for explaining a division rule applied to a temporary division portion in a unit subtitle sentence, and FIGS. 6 and 7 are diagrams for explaining a technique for detecting a synchronization of subtitle transmission timing for an announcement sound.

As the predetermined caption presentation format used in the embodiment of the present invention, the limit number of characters N per line is 15
The following description will proceed with an example of a subtitle presentation format in which presentation subtitles composed of two lines are collectively replaced with characters.

As described above, among subtitle programs currently being broadcast, an announcement manuscript is created in advance, and there are a number of programs that are presumed to have actual subtitles without any substantial modification of the manuscript. There is. For example, when actually examining an information program with subtitles called "Travel of the Earth", the announcement sound and subtitle content are almost the same, and it is estimated that almost the same manuscript is used for both the announcement and subtitle I can do it.

Therefore, the present inventors use the same manuscript for both the announcement and subtitles because the announcement sound and the contents of the subtitles are very similar, and the manuscript is digitized. Assuming a program, the proposed caption sentence text based on the caption by applying the technology for detecting the synchronization between the announcement sound and the caption text and the text segmentation technique using the Japanese feature analysis method proposed in the present invention. Has been conceived of a method for automatically dividing caption text, which can be automatically divided into presentation unit captions according to a predetermined caption presentation format.

Here, the background that led to the present invention will be described. When considering the problem of subtitle sentence text division from the viewpoint of subtitles that are easier to read and understand, it is obvious that subtitles are easier to read and understand. The question is what kind of thing is. We have not yet found a quantitatively clear answer to this question, but through valuable experience in producing experimental subtitle programs and subtitle evaluation experiments, qualitative but important factors are becoming clearer.

From the viewpoint of readability and comprehension of subtitles, in general, a certain number of characters or more is presented simultaneously,
It is said that it is good that the presentation lasts for the required time, but the number of characters and the presentation duration greatly affect how the presented subtitles are read.

For example, assuming that a hearing-impaired person watches a television program with subtitles, video information and audio information are alternately viewed through the sight, so that subtitles can be viewed only intermittently. Absent. For this reason, it is desirable to present the audio information as subtitles that are easier to read and understand, so that the ratio of viewing subtitles is reduced as much as possible, so that more video can be viewed accordingly.

The way of viewing subtitles in this case depends on the presentation format of the subtitles. For example, a case is shown in which a subtitle presentation format in which two-line presentation unit subtitles are exchanged at a time is attempted, and capture of all presented subtitles is attempted. Generally, pre-reading, post-reading, or both are performed centering on a reference subtitle character (for example, a character corresponding to the progress of a voice announcement).

The reason why the pre-reading, the post-reading, or both are performed is because there is an overlooking operation time in which the user is looking away from the subtitles including watching the video or blinking or looking aside. The length of the missed operation time is empirically considered to be about 0.5 to 2 seconds.

Here, assuming that the subtitle presentation speed is 200 characters / minute, the maximum time of 2 seconds is equivalent to about 7 characters. It can be seen that there is a risk of overlooking.

From the above, it is necessary that 14 characters continuous around the reference subtitle character be the minimum presentation unit, and the point of sight returns to the subtitle again, and the subtitle is read and recognized. Assuming 7 characters, 24
It can be seen that it is desirable to simultaneously present subtitles of about 29 characters on the screen. By the way, in the current subtitle broadcasting, one line is 15
Many characters are presented in two lines, and up to about 30 characters are presented.

According to the above analysis result, it is assumed that it takes about 2 seconds at the worst from the presentation of the subtitle to the actual reading, and if the subtitle having the number of characters of 7 or less is presented only for the time corresponding to the number of characters, May not be able to read this subtitle at all. For example, due to the characteristics of Japanese, negative words are placed at the end of sentences in negative sentences, so divisions in which this negative word part corresponds to the above state may have a very bad effect, and such divisions are possible. It must be avoided as much as possible.

As a countermeasure, it is desirable to apply a technique such as not dividing the number of characters into a small number or increasing the presentation time with a small number of characters.

The next problem is, for example, the handling of a silent section between sentences, that is, a pause. If there is a long pause in the caption text, it is highly likely that before and after the pause are caption texts related to mutually different contents, so it is not preferable to present a caption spanning the pose. Conversely, when there is a very short pause, it is more preferable to treat it as a continuous subtitle sentence before and after this pause, since there is a high possibility that the sentence is a subtitle sentence related to mutually common contents. For this reason, it is desirable to apply a caption sentence division method that takes into account the length of the pause time.

Further, it is desirable that a group of characters be presented on the same line without being divided as much as possible. Examples of this include not only ordinary words, but also continuous kanji, katakana, Arabic numerals, and alphabetic characters, such as (xxx) or "xxx"
Ruby, abbreviations for formal names, annotations, etc. are also included in this category.

In the division of the caption text, it is necessary to sufficiently consider the above-described elements. In the present invention, these elements are taken in and the division rules (line feed / line feed) in which the characteristics of Japanese are statistically set. By applying the page rule), it is possible to realize the division of the caption sentence text which can be said to be ideal.

Before the description of the present embodiment, terms used in the following description are defined. In the description of the present embodiment, the entire set of subtitle sentences to be presented is referred to as “subtitle text”. In the caption text, a subset of the caption text separated by appropriate punctuation is referred to as “unit subtitle text”, and the subtitle that is the presentation unit on the display screen of the display is referred to as “presentation subtitle”. say,
The individual subtitles of each line included in the presentation unit subtitle are referred to as “presentation unit subtitle line”, and when expressing any character in the presentation unit subtitle line, this is referred to as “subtitle character”.
Note that when a single presentation unit subtitle line is presented on the display screen, “presentation unit subtitle line” and “presentation unit subtitle line” are synonymous. In this case, the expression “presentation unit subtitle line” is used I will not do it.

First, a schematic configuration of an automatic subtitle program production system 11 that embodies the automatic subtitle text division method according to the present invention will be described with reference to FIG.

As shown in the figure, the automatic subtitle program production system 11 includes an electronic document recording medium 13, a synchronization detection device 15, an integration device 17, a morphological analysis unit 19, a division rule storage unit 21, , A program material VTR, for example, a digital video tape recorder (hereinafter, referred to as “D-VTR”) 23.

The digitized original recording medium 13 is composed of, for example, a hard disk storage device, a floppy disk device, or the like, and stores subtitle sentence text representing the entire set of subtitles to be presented. In this embodiment, since it is assumed that a substantially common digitized manuscript is used for both the announcement and the subtitle, the contents of the subtitle sentence text stored in the digitized manuscript recording medium 13 are presented. It is assumed that not only does it match the target subtitle, but also matches the announcement sound recorded on the material VTR.

The synchronization detecting device 15 provides a presentation unit subtitle sentence,
It has a function of detecting time synchronization with the announcement voice read out. More specifically, each time the presentation unit subtitle determined by the integration unit 17 is transmitted, the synchronization detection device 15 includes a validity verification function for verifying the validity of the presentation unit subtitle, and a validity verification function. When the verification result obtained by performing the function is invalid, the verification result reply function that returns the verification result to the integrating device 17 and the verification result obtained by performing the validity verification function are When it is appropriate, by referring to the announcement sound and the time code corresponding to the presentation unit subtitle fetched from the program material VTR, the timing information for each corresponding presentation unit subtitle, that is, the start point / end point time code is detected and detected. And a timing information detecting function of sending the start / end time codes to the integrating device 17.

Note that the synchronous detection of the start / end point time code assigned to each presentation subtitle in the above-described timing information detection function is performed by an announcement sound including a speech recognition process for an announcement sound developed and developed by the present inventors. It can be realized with high accuracy by applying the synchronization detection technology between the subtitle text and the subtitle text.

That is, as shown in FIG. 6, the flow of subtitle transmission timing detection is as follows. First, a subtitle sentence text described in a kana-kanji mixed sentence is generated using a reading technique used in speech synthesis or the like. Convert to a symbol string. The "Japanese reading system" is used for this conversion. Next, with reference to an acoustic model (HMM: Hidden Markov Model) that has been learned in advance, these phonetic symbol strings are converted into a speech model (HMM) called a word string pair model by a “speech model synthesis system”. Then, by performing the comparison and collation through the announcement sound to the word string pair model using the “maximum likelihood collation system”, the synchronization detection of the caption transmission timing is performed.

The algorithm (word string pair model) used for detecting the caption sending timing employs a keyword spotting technique. As a keyword spotting technique, a method has been proposed in which a posterior probability of a word is obtained by a forward / backward algorithm, and a local peak of the word likelihood is detected. As shown in FIG. 7, the word string pair model is applied to the point where it is desired to synchronize subtitles and audio, that is, word string 1 (Keywords1) and word string 2 (Keywords2) are connected before and after the synchronization point. The model is designed to observe the likelihood at the middle point (B) of the word string, detect its local peak, and obtain the utterance start time of the word string 2 with high accuracy.
The word sequence is formed by connecting phoneme HMMs, and the garbage (Garbage) portion is formed as parallel branches of all phoneme HMMs. When the announcer reads the manuscript, a pause is inserted between the word strings 1 and 2 because the position of the breath is arbitrarily determined so that the contents can be easily understood. The detection of the pause time can be easily achieved by a well-known technique from the start and end time codes in which a sound and its time code are supplied from the material VTR and the sound level is continuous below a specified level.

The unifying device 17 stores the digitized original recording medium 1
3. A unit subtitle sentence extraction function for sequentially extracting unit subtitle sentences based on the required number of characters starting from the beginning of the subtitle sentence text read from unit 3, and a unit subtitle extracted by using the unit subtitle sentence extraction function A presentation unit subtitle conversion function of converting a sentence into a presentation unit subtitle according to a desired presentation format, and a presentation sent from the synchronization detection device 15 for the presentation unit subtitle converted by exhibiting the presentation unit subtitle function. A timing information adding function of adding each time code of a start point / end point, which is timing information for each unit subtitle. Note that the required number of characters starting from the beginning of the sentence means that when the number of characters N per line is assumed to be 15 characters, for example, a range of about 70 to 90 subtitle characters with an upper limit of 6N characters is a unit of text sentence or processing. An appropriate character number range can be selected in consideration of the data amount and the like.

The morphological analysis unit 19 divides a unit subtitle sentence described in a kanji kana mixed sentence into morphemes, and expresses a morpheme for each morpheme divided by performing the dividing function. It has an additional information addition function to add additional information such as shape, part of speech, reading, and standard expression, and an information element sequence acquisition function to group each morpheme into clauses and clauses and obtain some information element strings. ing. As a result, the unit caption sentence is composed of a surface sequence, a symbol sequence (part of speech), a standard sequence,
And an information element sequence.

As shown in FIG. 5, the division rule storage unit 21 has a function of storing a division rule which is referred to when optimizing a line feed / page break position for a unit caption sentence. .

The D-VTR 23 has a function of reproducing and outputting video, audio, and their time codes from a program material VTR tape in which the program material is recorded.

Next, the internal configuration of the integrating device 17 which plays a major role in the automatic subtitle program production system 11 will be described.

The integrating device 17 includes a unit subtitle sentence extracting unit 33
, Presentation unit subtitle conversion unit 35, timing information addition unit 3
7 are included.

The unit subtitle sentence extracting unit 33 reads, for example, 70 to 90 units of subtitle sentence text read from the digitized original recording medium 13 and arranged in the order of presentation time.
A text sentence that is a unit of subtitle sentence to be presented that has at least the number of characters included in the presentation unit subtitle line with the subtitle character level as a guide, and that uses the added delimitable part information etc. as a processing unit Are sequentially extracted. Note that, as the delimitable portion information, morphological analysis data with phrase data obtained by the morphological analysis unit 19 and division rules (line feed / page break data) stored in the division rule storage unit 21 can also be used. .

The presentation unit captioning unit 35 generates a unit caption based on the unit caption sentence extracted by the unit caption sentence extraction unit 33, delimitable portion information added to the unit caption sentence, information from the synchronization detection device 15, and the like. It has a presentation unit subtitle conversion function of converting the unit subtitle sentences extracted by the sentence extraction unit 33 into at least one or more presentation unit subtitles according to a desired presentation format.

The timing information adding unit 37 compares the presentation unit subtitles converted by the presentation unit subtitle conversion unit 35 with the start point / end point time, which is the timing information for each presentation unit subtitle sent from the synchronization detection device 15. It has a timing information adding function for giving a code.

Next, a subtitle sentence text dividing procedure according to the present invention will be described with reference to the operation flowchart shown in FIG.

In step S1, for example, 6N characters (= 90 characters) starting from the beginning of the subtitle sentence text
For the required number of characters range, the silent section existing at the end of the sentence having a length exceeding the first predetermined time t1 such as one second, that is, the first sentence end pause point Pt1 and all the punctuation points are extracted. Among the extracted first sentence end pause points Pt1, in particular, the sentence end pause point having a longer time than the first predetermined time t1 and exceeding the second predetermined time t2 such as 2 seconds, for example, is set as the first sentence end pause point. The second sentence pause point Pt2 will be referred to as Pt2, and the punctuation marks excluding these last sentence pause points Pt1 and Pt2 will be referred to as Pk.

In step S2, it is determined whether or not the second sentence end pause point Pt2 exists within the required number of characters range. As a result of this investigation judgment, the second sentence end pause point Pt
Step S3 when it is determined that No. 2 exists.
On the other hand, when it is determined that the second sentence end pause point Pt2 does not exist, the process proceeds to step S4.

As a result of the investigation in step S2, when it is determined that the second sentence end pause point Pt2 exists, in step S3, the second character that appears first from the beginning of the sentence in the required character number range is calculated. The range up to the sentence end pause point Pt2 is extracted as a unit caption sentence.

On the other hand, as a result of the investigation in step S2, when it is determined that the second sentence end pause point Pt2 does not exist, in step S4, the last character number appears from the beginning of the sentence in the required character number range. The range up to the first sentence end pause point Pt1 is extracted as a unit caption sentence.

The processing in steps S1 to S4 described above is processing for extracting unit subtitle sentences. In the present invention, the unit subtitle conversion is performed by treating the unit subtitle sentences extracted in the extraction process as one processing unit. The processes described below are sequentially executed.
In this extraction processing, in extracting unit caption sentences within the required character range from caption sentence texts, the purpose is to avoid the situation where subtitles related to mutually different contents are mixed in a certain presentation unit caption. Therefore, it is preferable that the extracted unit caption text is an aggregate of caption texts related to the contents of a common block.

Therefore, in this extraction processing, the second pause, which has a relatively long interval which can be regarded as a recommended page break, which tends to be inserted between unit subtitle sentences relating to mutually different contents. Focusing on the end-of-sentence pause point Pt2 and extracting the range from the beginning of the sentence to the second end-of-sentence pause point Pt2 as a unit subtitle sentence, the unit subtitle sentence relating to the contents of the block is intentionally extracted. To be extracted.

Also, if the result of the investigation determination in step S2 is that there is no second sentence end pause point Pt2 that is a pose with a relatively long interval that can be regarded as a recommended page break, , The second sentence end pause point Pt
1st sentence end pause point Pt1 which is a pose having a certain length interval that can be regarded as a recommended line feed instead of 2
By extracting the range from the beginning of the sentence to the first sentence end pause point Pt1 appearing last from the beginning of the sentence as a unit subtitle sentence in the required number of characters range, the case where the second sentence end pause point Pt2 does not exist is obtained. Even if there is, a unit caption sentence related to the contents of a group is intentionally extracted as much as possible.

In step S5, the unit caption sentence extracted in step S3 or S4 is replaced with the first sentence end pause point Pt.
By sequentially performing line feeds at the position of No. 1, a temporary division of the unit subtitle sentence is performed.

In step S6, for each of the plurality of lines provisionally divided in step S5, the number of characters per line is, for example, N-3 characters (= 12 characters) smaller than the limited number of characters N per line defined in a predetermined subtitle presentation format. The number of characters in each line is sequentially determined based on whether or not the number of characters is equal to or more than a first predetermined number of characters. As a result of the determination of the number of characters in each line, there is a corresponding line in which the number of characters per line satisfies the condition of the first predetermined number of characters or more. If it is determined that the line does not exist, the process proceeds to step S8. The determination of the number of characters in each line in step S6 is to determine whether or not the number of characters included in each of the plurality of lines provisionally divided in step S5 converges to an appropriate number of characters when considering the limited number of characters N per line.

As a result of the determination of the number of characters in each line in step S6, when it is determined that the corresponding line exists, the number of characters from the head of each of the corresponding lines is set to the first predetermined number of characters N
By performing a line feed immediately after reaching −3 characters (= 12 characters), the unit subtitle sentence is provisionally divided. After this re-line feed processing, the process returns to step S6 until the line no longer exists. Steps S7 to S7 are repeated. Note that the line feed point at step S7 is replaced with the line feed point Pp.
I will call it.

The processing of steps S5 to S7 described above is the provisional division processing of the unit caption sentence. An important point to be considered in performing the provisional division processing is that a line feed is performed at an appropriate place.
And that the number of characters per line converges within the limited number of characters N per line defined in a predetermined subtitle presentation format.

Therefore, as shown in FIG. 3, for example, as for the former line feed at a suitable position, a pause having a certain length interval which can be regarded as a recommended line feed position, which tends to be inserted at a break in the text. Is the first sentence end pause point Pt
Focusing on 1, the unitary subtitle sentences are sequentially line-feeded at the position of the first sentence end pause point Pt1. On the other hand, with regard to the latter convergence of the limited number of characters, the number of characters per line is equal to the first predetermined number of characters N-. For each line that meets the condition of 3 or more characters (= 12 characters), the number of characters per line is mechanically re-lined immediately after the number of characters from the top reaches the first predetermined number of characters. , Limit number of characters N
In consideration of convergence to an appropriate number of characters that does not exceed, the unit caption sentence is provisionally divided at an appropriate place.

In step S8, an odd / even judgment is made as to whether the total number of lines of the unit caption sentence provisionally divided into a plurality of lines in steps S5 to S7 is odd or even. As a result of the odd / even judgment, the total number of lines is odd. In the case of, the process proceeds to step S9,
If the total number of rows is even, the process proceeds to step S12. The odd / even judgment is performed, for example, in a case where a subtitle presentation format in which two-line presentation unit subtitles are totally exchanged is adopted as a predetermined subtitle presentation format, in order to determine whether the final presentation unit subtitle is a single line. It is.

As a result of the odd / even determination in step S8, when it is determined that the total number of rows is odd, the process proceeds to step S8.
9, whether the number of characters in the last line of the provisionally divided unit caption text is equal to or greater than a second predetermined number of characters such as N / 2 characters (= 8 characters, but the fraction is rounded up), which is smaller than the limited number of characters N If the result of the final line character number determination is that the number of characters in the final line does not meet the condition of the second predetermined number of characters (N / 2 characters) or more, step S10 is performed. On the other hand, when it is determined that the condition is satisfied, the process proceeds to step S
Proceed to 12.

As a result of determining the number of characters on the last line in step S9,
When it is determined that the number of characters in the last line does not meet the condition of the second predetermined number of characters (N / 2 characters) or more, in step S10, the first sentence end pause point Pt1 is calculated from the end of the unit subtitle sentence. , Check for the presence or absence of a period Pk or a line feed Pp according to this priority, and insert a blank line between the line including the first point between odd and even lines and the subsequent line. Then, the continuation is sent to the next page, and the last line is divided into two lines.

In step S11, step S10
The number of characters in the immediately preceding line of the blank line inserted in is determined to be greater than or equal to the second predetermined number of characters (N / 2 characters), and the number of characters in the immediately preceding line is determined as the result of the immediately preceding line character number determination. When it is determined that the condition does not satisfy the condition of the second predetermined number of characters or more, the process returns to step S10 and cancels the immediately preceding blank line insertion, and the processing of steps S10 to S11 is repeated. Are repeatedly executed until the number of characters in the immediately preceding line reaches a condition equal to or greater than a second predetermined number of characters (N / 2 characters).

The processing in steps S9 to S11 is blank line insertion processing, and this blank line insertion processing is intended to promote accurate and reliable reading and grasping of subtitle presentation contents. More specifically, the case where the total number of lines in the unit subtitle sentence is an odd number and the number of characters in the last line does not meet the condition of the second predetermined number of characters (N / 2 characters) or more is as follows.
This means that the final presentation unit subtitle is a single line and the number of characters in this last line is relatively small. In this case, the presentation duration time of a certain presentation unit subtitle is determined by the number of subtitle characters included in it. Because of the principle that the subtitle depends on the size of the subtitles, the presentation duration of the last line is inevitably shortened. In particular, in the case of a negative sentence, if the negation part is overlooked due to the characteristic of Japanese such that the negation word is placed at the end of the sentence, the original meaning may be misunderstood.

Therefore, in such a case, the first sentence end pause point Pt1 and the period P
k or the presence or absence of a line feed point Pp is checked in accordance with this priority order. Of these points, for example, as shown in FIG. By inserting blank lines, the presentation duration of the last line is intentionally lengthened to be longer than originally intended, thereby avoiding the possibility of inadvertently overlooking the caption presentation content of the last line, This facilitates accurate and reliable reading and comprehension of the subtitle presentation contents.

In step S12, the sub-line break point is optimized by applying the division rule relating to the recommended line break and page break point for the unit subtitle sentence, with respect to the line break point Pp. The sentence text is automatically divided into presentation unit subtitles according to a predetermined subtitle presentation format. Here, the above-described division rule (line feed / page break data)
5, the morpheme part of speech immediately before a line break or page break with a natural feeling and an example of its frequency are shown. As shown in the figure, the recommended line break / page break defined by the division rule (line feed / page break data) is first after the punctuation mark, secondly after the reading point, and thirdly between clauses. And fourthly, between morpheme parts of speech, and when applying the division rule (line feed / page break data), it is preferable to apply the priority from the top of the above-mentioned description order with priority. In this way, it is possible to realize automatic division of the caption sentence text that is optimized with high accuracy in accordance with the actual situation.

In step S12, the purpose of optimizing the line feed point applying the division rule is that the first sentence end pause point Pt1, which is the original line feed point, qualifies as "after the period" in the division rule. Although the condition is already satisfied and there is no room for optimization to which the condition is applied, the condition is mechanically applied immediately after the number of characters from the head reaches the first predetermined number of characters (N-3 characters). At the line feed point Pp,
It doesn't necessarily meet the eligibility criteria for the split rule, and there is room for optimization to apply,
By executing the optimization of the re-line feed part Pp, as a result of guaranteeing a line feed at an appropriate part of the unit sub-title text, automatic division of the sub-title text into presentation sub-titles according to a predetermined sub-title presentation format is ensured. I am trying to do it.

In step S13, a subsequent presence / absence determination is performed on the presence / absence of a subtitle sentence subsequent to the unit subtitle sentence extracted in step S3 or S4, and as a result of the subsequent presence / absence determination, it is determined that a subsequent subtitle sentence exists. Is returned to step S1, and the following processing is repeated for the subsequent subtitle sentence. On the other hand, when it is determined that there is no subsequent subtitle sentence, the automatic subtitle sentence text division processing ends. It is.

Thus, it is possible to execute automatic division processing for all subtitle sentences included in the subtitle sentence text.

As described above, according to the automatic subtitle sentence text division method according to the present invention, the subtitle base is obtained by applying the text division technique using the Japanese feature analysis method proposed in the present invention. The caption text can be automatically divided into presentation unit captions according to a predetermined caption presentation format.

Further, according to the automatic subtitle text division method according to the present invention, among the unit subtitle texts appropriately extracted from the subtitle text, the final presentation unit subtitle is a single line. If the number of characters in the line is relatively small, the presentation duration time related to the last line is intentionally lengthened to be longer than the original one by inserting a blank line between appropriate lines in the extracted unit subtitle sentences. As a result, a situation in which the caption presentation content of the last line is inadvertently overlooked can be avoided as much as possible. As a result, accurate and reliable reading and comprehension of the caption presentation content can be promoted.

It is needless to say that the present invention is not limited to the example of the above-described embodiment, but can be embodied in other forms by making appropriate changes within the scope of the claims.

[0103]

As described in detail above, according to the first aspect of the present invention, the subtitles are formed by applying the text segmentation technique using the Japanese feature analysis technique proposed in the present invention. It is possible to obtain an automatic division method of caption text that can automatically divide caption text into presentation subtitles according to a predetermined caption presentation format.

According to the first aspect of the present invention, it is possible to avoid inadvertently overlooking the subtitle presentation content of the last line as much as possible. Can be promoted.

According to the second aspect of the present invention, even if the second sentence end pause point does not exist in the required number of characters range from the beginning of the sentence, the unit caption sentence relating to the contents of a group as much as possible. Can be intentionally extracted.

Further, according to the third aspect of the present invention, it is possible to avoid as much as possible the inadvertent overlooking of the subtitle presentation contents of the immediately preceding line. Can be promoted.

Further, according to the fourth aspect of the present invention, it is possible to execute automatic division processing for all subtitle sentences included in the subtitle text.

Further, according to the fifth aspect of the present invention, it is possible to realize automatic division of caption sentence text that is optimized with high precision in accordance with the actual situation.

Further, according to the invention of claim 6, for example, when a standard caption presentation format in which the limit number of characters per line is 15 characters is adopted, one line per presentation unit subtitle line is included. As a result that the number of subtitle characters converges in the range of 12 to 15 characters, it is possible to realize automatic division of subtitle sentence text having a good appearance when presenting subtitles.

According to the seventh aspect of the present invention, for example, when a standard caption presentation format in which the number of characters per line is limited to 15 is adopted, the number of characters for which the number of subtitle characters per line is considered to be small Is 7 characters, and the threshold number of characters is, for example, assuming that the overlooking operation time length per one look away from the subtitle is about 0.5 to 2 seconds and the subtitle presentation speed is 200 characters / min. As a result, the maximum value of the oversight operation time of 2 seconds is equivalent to about 7 characters, and from this result, it has been verified that there is a possibility that a single oversight operation may miss 7 subtitle characters. As a result, it can be said that the number of characters is extremely reasonable, and as a result that it is possible to expect at a high level the effect of avoiding inadvertently overlooking the subtitle presentation content of the relevant line as a result, accurate and reliable character It exhibits an extremely excellent effect that the reading understanding of the presentation content can be dramatically accelerated.

[Brief description of the drawings]

FIG. 1 is a functional block configuration diagram of an automatic subtitle program production system that embodies an automatic subtitle text division method according to the present invention.

FIG. 2 is a flowchart illustrating a subtitle sentence text division procedure;

FIG. 3 is a diagram illustrating a state where a unit caption sentence is provisionally divided at an appropriate position.

FIG. 4 is a diagram illustrating a state where a blank line is inserted at an appropriate position in a unit caption sentence.

FIG. 5 is a diagram for explaining a division rule applied to a temporary division position in a unit caption sentence;

FIG. 6 is a diagram provided for describing a technique for detecting a synchronization of subtitle transmission timing for an announcement sound;

FIG. 7 is a diagram provided for describing a technique for detecting a synchronization of subtitle transmission timing with respect to an announcement sound;

FIG. 8 is an explanatory diagram relating to a current subtitle production flow and an improved current subtitle production flow.

[Description of Signs] 11 Automatic closed-caption program production system 13 Electronic document recording medium 15 Synchronization detection device 17 Integration device 19 Morphological analysis unit 21 Division rule storage unit 23 Digital video tape recorder (D-V)
TR) 33 unit subtitle sentence extraction unit 35 presentation unit subtitle conversion unit 37 timing information addition unit

 ──────────────────────────────────────────────────続 き Continued on the front page (71) Applicant 000006013 Mitsubishi Electric Corporation 2-3-2 Marunouchi, Chiyoda-ku, Tokyo (71) Applicant 000004352 Japan Broadcasting Corporation 2-2-1 Jinnan, Shibuya-ku, Tokyo (72 Inventor Eiji Sawamura 2-31-19 Shiba, Minato-ku, Tokyo Communication and Broadcasting Corporation (72) Inventor Takao Kadoma 2-31-19 Shiba in Minato-ku Tokyo, Japan Communication and Broadcasting Corporation (72) Inventor Takahiro Fukushima Tokyo 2-31-19 Shiba, Minato-ku, Tokyo Communication and Broadcasting Organization (72) Inventor Ichiro Maruyama 2-31-19 Shiba, Minato-ku, Tokyo Inside (72) Inventor Terumasa Ehara 2 Shiba, Minato-ku, Tokyo −31−19 Communications and Broadcasting Corporation (72) Inventor Katsuhiko Shirai 2-31-19, Shiba, Minato-ku, Tokyo Communications and Broadcasting Corporation F-term (reference) 5C023 AA18 AA38 BA11 BA16 CA01 CA05 5C025 CA09 CB10 DA10

Claims (7)

[Claims] 1. A method of dividing a subtitle text used to produce at least a subtitle text that is a basis of a subtitle when producing a subtitle program, into a presentation unit subtitle according to a predetermined subtitle presentation format, In the subtitle sentence text, all of the first sentence end pause point and the period which exceed the first predetermined time are extracted for the required number of characters starting from the beginning of the sentence, and the extracted first sentence end is extracted. Of the pose points,
The presence / absence of a second sentence end pause point having a length longer than the second given time which is longer than the given time is examined and determined. As a result of this examination, the second sentence pause point is present. Is determined, the range from the beginning of the sentence to the second sentence end pause point that appears first from the beginning of the sentence is extracted as a unit subtitle sentence, and the extracted unit subtitle sentence is The unit subtitle sentence is provisionally divided by sequentially performing line feed at the end of the sentence pause point, and the number of characters per line is defined in a predetermined subtitle presentation format for each of the plurality of provisionally divided lines. Each line character number determination is sequentially performed according to whether or not the number of characters is equal to or more than a first predetermined number of characters less than the limit number of characters per line. As a result of the determination of each line character number, the number of characters per line meets the condition of the first predetermined number of characters or more. When it is determined that a line exists, a line break is performed again at a position immediately after the number of characters from the head reaches the first predetermined number of characters for each of the lines, thereby temporarily dividing the unit subtitle sentence. The odd / even judgment is performed as to whether the total number of lines of the unit subtitle text provisionally divided into the plurality of lines is odd or even. As a result of the odd / even judgment, it is determined that the total number of lines is odd. In the temporary subtitle sentence, a final line character number determination is performed as to whether or not the number of characters in the last line is equal to or greater than a second predetermined number of characters that is smaller than the limited number of characters. When it is determined that the number of characters in the last line does not meet the condition of the second predetermined number of characters or more, the presence of the first sentence end pause point, the period, or the line feed point from the end of the unit subtitle sentence. Investigate the presence or absence according to this priority, and For each point, insert a line containing the first point between odd and even lines and a blank line between subsequent lines, and recommend line breaks and page breaks for the unit subtitle sentence at the line break point. Optimizing a line feed portion by applying a division rule pertaining to a portion, thereby automatically dividing the subtitle text into presentation unit subtitles according to a predetermined subtitle presentation format; Automatic text division method. 2. The method for automatically dividing caption text according to claim 1, wherein the required character number range is set when it is determined that the second sentence end pause point does not exist as a result of the investigation determination. In the above, the range from the beginning of the sentence to the first sentence end pause point that appears last is extracted as a unit subtitle sentence, and the following processing including provisional division of the unit subtitle sentence is performed on the extracted unit subtitle sentence. A method for automatically dividing caption text, which is performed. 3. The method for automatically dividing caption text according to claim 1, wherein the first sentence end pause point, the punctuation mark, or the point including a line feed point is included. After inserting a blank line between the line that includes the first point between the odd and even lines and the subsequent line, the number of characters in the line immediately before the inserted blank line is further defined as a line defined by the prescribed subtitle presentation format. A determination is made as to whether or not the number of characters in the immediately preceding line is equal to or greater than a second predetermined number of characters, which is smaller than the hit limit character number. Is determined from the end of the sentence of the unit subtitle sentence, the presence or absence of a first sentence end pause point, a punctuation point, or a line feed point is checked in accordance with this priority order. After the point that appeared, A blank line is inserted between the line containing the dot and the subsequent line, and after this blank line is inserted, the processing of the preceding line character number determination and the subsequent steps are performed. 2. A method for automatically dividing a caption sentence text, wherein the method is repeatedly executed until a condition equal to or more than a predetermined number of characters is met. 4. The method for automatically dividing caption text according to claim 1, wherein a line feed / page break recommendation for the unit caption text is made for the re-feed point. After executing the optimization of the line feed point by applying the division rule pertaining to the location, the subsequent presence / absence determination is performed according to the presence / absence of the subtitle text following the extracted unit subtitle text. As a result of the subsequent presence / absence determination, When it is determined that a subsequent subtitle sentence exists, the process returns to the initial processing step, and the following processing is repeated for the subsequent subtitle sentence, while it is determined that the subsequent subtitle sentence does not exist. And automatically ending the subtitle sentence text dividing process. 5. The method for automatically dividing caption text according to claim 1, wherein a line feed / page break recommendation for the unit caption text is performed at the re-feed point. In optimizing the line breaks by applying the division rules for the sections, the recommended line breaks and page breaks defined by the division rules are after the punctuation marks, after the punctuation marks, between the phrases, Automatic division of subtitle sentence text characterized by including any one or more combinations among morpheme parts of speech, and applying the division rule preferentially from the beginning of the description order. Method. 6. The method for automatically dividing caption text according to claim 1, wherein a limit number of characters N per line defined in the predetermined caption presentation format is 15 characters. In this case, the first predetermined number of characters is 12 (= N−3) characters, wherein the caption text is automatically divided. 7. The method for automatically dividing caption text according to claim 1, wherein the limited number of characters N per line defined in the predetermined caption presentation format is 15 characters. In this case, the second predetermined number of characters is 8 (= N / 2; however, rounded up to the nearest decimal place).