- Number
- 11847425
- Published
- 2023-12-19
- Filed
- 2018-08-01
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Doggett; Erika
- CPC
- G06F3/167; G06F40/205; G06F40/40; G06F40/51; G06F40/55; G06F40/58; G10L15/1822; G10L15/22; G10L15/26; G10L21/00; G10L25/57; H04N21/251; H04N21/440236; H04N21/466; H04N21/4856; H04N21/4884; H04N21/8106
- Verdict
- Set aside generic machine translation, localization plumbing
- Source
- Google Patents · FreePatentsOnline
Abstract
A process receives, with a processor, audio corresponding to media content. Further, the process converts, with the processor, the audio to text. In addition, the process concatenates, with the processor, the text with one or more time codes. The process also parses, with the processor, the concatenated text into one or more text chunks according to one or more subtitle parameters. Further, the process automatically translates, with the processor, the parsed text from a first spoken language to a second spoken language. Moreover, the process determines, with the processor, if the language translation complies with the one or more subtitle parameters. Additionally, the process outputs, with the processor, the language translation to a display device for display of the one or more text chunks as one or more subtitles at one or more times corresponding to the one or more time codes.
Background
BACKGROUND 1. Field (1) This disclosure generally relates to the field of language translation. 2. General Background (2) Conventional machine translation systems typically allow for computerized translation from text and/or audio in a first language (e.g., English) into text and/or audio of a second language (e.g., Spanish). For example, some machine translation systems allow for a word-for-word translation from a first language into a second language. Yet, such systems typically focus only on pure linguistic translation. SUMMARY (3) In one aspect, a computer program product comprises a non-transitory computer readable storage device having a computer readable program stored thereon. The computer readable program when executed on a computer causes the computer to receive, with a processor, audio corresponding to media content. Further, the computer is caused to convert, with the processor, the audio to text. In addition, the computer is caused to concatenate, with the processor, the text with one or more time codes. The computer is also caused to parse, with the processor, the concatenated text into one or more text chunks according to one or more subtitle parameters. Further, the computer is caused to automatically translate, with the processor, the parsed text from a first spoken language to a second spoken language. Moreover, the computer is caused to determine, with the processor, if the language translation complies with the one or more subtitle parameters. Additionally
Claims
1. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to: receive audio corresponding to media content; convert the audio to text; parse the text into one or more first text chunks in a first language according to one or more subtitle parameters; perform a first language translation, via a language translation system, of the one or more first text chunks in the first language to one or more second text chunks in a second language; determine that a particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters; in response to determining that the particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters, generate a modified particular text chunk that complies with the one or more subtitle parameters, wherein generating the modified particular text chunk comprises: generating a confidence score for each of a plurality of potential modified text chunks, iterating through each of the plurality of potential modified text chunks, from a highest to a lowest confidence score, until a first potential modified text chunk satisfies the one or more subtitle parameters, and selecting the first potential modified text chunk as the modified particular text chunk; and output the one or more second text chunks, including the modified particular text chunk, to a display device for display as one or more subtitles at one or more times corresponding to one or more time codes associated with the one or more first text chunks. ||
7. An apparatus comprising: a memory storing instructions; and a processor that is coupled to the memory and, when executing the instructions, is configured to: receive audio corresponding to media content, convert the audio to text, parse the text into one or more first text chunks in a first language according to one or more subtitle parameters, perform a first language translation, via a language translation system, of the one or more first text chunks in the first language to one or more second text chunks in a second language, determine that a particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters, in response to determining that the particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters, generate a modified particular text chunk that complies with the one or more subtitle parameters, wherein generating the modified particular text chunk comprises: generating a confidence score for each of a plurality of potential modified text chunks, iterating through each of the plurality of potential modified text chunks, from a highest to a lowest confidence score, until a first potential modified text chunk satisfies the one or more subtitle parameters, and selecting the first potential modified text chunk as the modified particular text chunk, and output the one or more second text chunks, including the modified particular text chunk, to a display device for display as one or more subtitles. ||
14. A method comprising: receiving audio corresponding to media content; converting the audio to text; parsing the text into one or more first text chunks in a first language according to one or more subtitle parameters; performing a first language translation, via a language translation system, of the one or more first text chunks in the first language to one or more second text chunks in a second language; determining that a particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters; in response to determining that the particular text chunk of the one or more second text chunks does not comply with the one or more subtitle parameters, generating a modified particular text chunk that complies with the one or more subtitle parameters, wherein generating the modified particular text chunk comprises: generating a confidence score for each of a plurality of potential modified text chunks, iterating through each of the plurality of potential modified text chunks, from a highest to a lowest confidence score, until a first potential modified text chunk satisfies the one or more subtitle parameters, and selecting the first potential modified text chunk as the modified particular text chunk; and outputting the one or more second text chunks, including the modified particular text chunk, to a display device for display as one or more subtitles at one or more times corresponding to one or more time codes associated with the one or more first text chunks.