System and method of subtitling by dividing script text into two languages

1. A method of subtitling, comprising the steps of:

obtaining an audio file of dialogue in a first language;

obtaining a file of script text corresponding to the dialogue in the audio file in the same first language;

determining, by one or more processors of a computing device, a timing correspondence between dialogue in the audio file and words in the script text;

detecting at least a first pause during performance of the dialogue in the audio file;

defining, by the one or more processors, a respective breakable point in the script text corresponding to the or each detected pause;

dividing, by the one or more processors, the script text out into a sequence of subtitle lines of text responsive to the location of one or more of the defined breakable points;

obtaining a file of script text corresponding to the dialogue in the audio file in a different second language;

obtaining the sequence of subtitle lines of text divided out of the script text of the first language, the sequence comprising a characteristic number of lines;

detecting, by the one or more processors corresponding features of the text between both languages;

dividing, by the one or more processors, the script text in the second language into a sequence of subtitle lines of text having the same characteristic number of lines, the points of division being responsive to the correspondence of features of the text between both languages; and

outputting the sequence of subtitle lines of text for presentation on a display device.

2. A method of subtitling according to claim 1 , comprising the step of:

setting a maximum length for a line of subtitle text;

and wherein the step of dividing the script text out into a sequence of subtitles comprises:

dividing the remaining script text at the last breakable point in the remaining script text whose position precedes the position in the remaining script text equal to the maximum length of line of subtitle text.

3. A method of subtitling according to claim 1 , in which the step of detecting at least a first pause comprises the step of:

classifying the pause as a short pause or a long pause according to whether the pause exceeds a predetermined threshold duration.

4. A method of subtitling according to claim 3 , in which the step of defining a respective breakable point comprises the step of:

defining a breakable point where a pause is classified as a short pause, and defining a break point where a pause is classified as a long pause.

5. A method of subtitling according to claim 4 which the step of dividing the script text out into a sequence of subtitles comprises:

dividing the remaining script text at the next break point in the remaining script text.

6. A method of subtitling according to claim 1 , comprising the step of:

defining a respective timing for the second and any subsequent subtitle line with respect to the start of the dialogue in the audio file based upon the timing of the or each pause corresponding to the or each division of the script text.

7. A method of subtitling according to claim 1 , in which the step of detecting corresponding features comprises detecting punctuation at the end of subtitle lines of text in the first language within the script text in the second language.

8. A subtitle generating apparatus, comprising:

one or more computer processors, adapted to:

obtain an audio file of dialogue in a first language;

obtain a file of script text corresponding to the dialogue in the audio file in the same first language;

determine a timing correspondence between dialogue in the audio file and words in the script text;

detect at least a first pause during performance of the dialogue in the audio file;

define a respective breakable point in the script text corresponding to the or each detected pause;

divide the script text out into a sequence of subtitle lines of text responsive to the location of one or more of the defined breakable points;

obtain a file of script text corresponding to the dialogue in the audio file in a different second language;

obtain the sequence of subtitle lines of text divided out of the script text of the first language, the sequence comprising a characteristic number of lines;

detect corresponding features of the text between both languages;

divide the script text in the second language into a sequence of subtitle lines of text having the same characteristic number of lines, the points of division being responsive to the correspondence of features of the text between both languages

output the sequence of subtitle lines of text for presentation on a display device.

9. The subtitle generating apparatus of claim 8 , in which one or more of said computer processors is adapted to:

set a maximum length for a line of subtitle text;

and divide the remaining script text at the last breakable point in the remaining script text whose position precedes the position in the remaining script text equal to the maximum length of line of subtitle text.

10. The subtitle generating apparatus of claim 8 , in which one or more of said computer processors is adapted to:

classify the pause as a short pause or a long pause according to whether the pause exceeds a predetermined threshold duration;

define a breakable point where a pause is classified as a short pause, and define a break point where a pause is classified as a long pause; and

divide the remaining script text at the next break point in the remaining script text.

11. The subtitle generating apparatus of claim 8 , in which one or more of said computer processors is adapted to:

detect corresponding features by detecting punctuation at the end of subtitle lines of text in the first language within the script text in the second language.

12. A tangible non-transitory computer program product comprising processor instructions that when implemented cause one or more computer processors to carry out steps comprising:

obtaining an audio file of dialogue in a first language;

obtaining a file of script text corresponding to the dialogue in the audio file in the same first language;

determining a timing correspondence between dialogue in the audio file and words in the script text;

detecting at least a first pause during performance of the dialogue in the audio file;

defining a respective breakable point in the script text corresponding to the or each detected pause;

dividing the script text out into a sequence of subtitle lines of text responsive to the location of one or more of the defined breakable points;

obtaining a file of script text corresponding to the dialogue in the audio file in a different second language;

obtaining the sequence of subtitle lines of text divided out of the script text of the first language, the sequence comprising a characteristic number of lines;

detecting corresponding features of the text between both languages;

dividing the script text in the second language into a sequence of subtitle lines of text having the same characteristic number of lines, the points of division being responsive to the correspondence of features of the text between both languages; and

outputting the sequence of subtitle lines of text for presentation on a display device.