Machine translation system for entertainment and media
AssigneeDisney Enterprises, Inc.
InventorErika Doggett
Life of this patent
Estimating the term…
Abstract
Techniques for generating translated audio output based on media content are disclosed. Text is accessed corresponding to media content. One or more untranslated mouth shape indicia are determined based on the text. The text is parsed into one or more text chunks when one or more dubbing parameters are met. The parsed text is translated from a first spoken language to a second spoken language. One or more translated mouth shape indicia are determined. The one or more translated mouth shape indicia and the one or more untranslated mouth shape indicia are compared based on a predetermined tolerance threshold. A translated audio output is generated based on the translated text.
Claims20
At least one non-transitory computer-readable medium carrying instructions that, when executed by a processor, cause the processor to:
- receive audio corresponding to media content;
- convert the audio to text;
- concatenate the text with one or more time codes and one or more untranslated mouth shape indicia;
- parse the concatenated text into one or more text chunks when one or more dubbing parameters are met;
- automatically translate the one or more text chunks from a first spoken language to a second spoken language;
- automatically generate one or more translated mouth shape indicia;
- determine whether the one or more translated mouth shape indicia match the one or more untranslated mouth shape indicia within a predetermined tolerance threshold;
- generate a translated audio based on the one or more translated mouth shape indicia matching the one or more untranslated mouth shape indicia within the predetermined tolerance threshold;
- generate modified media content by placing the translated audio based on the one or more time codes in place of the audio corresponding to the media content;
- and
- output the modified media content.
A computing system comprising:
- at least one processor;
- and
- at least one non-transitory memory carrying instructions that, when executed by the at least one processor, cause the computing system to:
- access text corresponding to media content;
- determine one or more untranslated mouth shape indicia based on the text;
- parse the text into one or more text chunks when one or more dubbing parameters are met;
- translate the parsed text from a first spoken language to a second spoken language;
- determine one or more translated mouth shape indicia;
- compare the one or more translated mouth shape indicia and the one or more untranslated mouth shape indicia based on a predetermined tolerance threshold;
- generate a translated audio based on the translated text;
- generate modified media content by placing the translated audio in place of an audio corresponding to the media content;
- and
- output the modified media content.
A computer-implemented method comprising:
- accessing text corresponding to media content;
- determining one or more untranslated mouth shape indicia based on the text;
- parsing the text into one or more text chunks when one or more dubbing parameters are met;
- translating the parsed text from a first spoken language to a second spoken language;
- determining one or more translated mouth shape indicia;
- comparing the one or more translated mouth shape indicia and the one or more untranslated mouth shape indicia based on a predetermined tolerance threshold;
- generating a translated audio based on the translated text;
- generate modified media content by placing the translated audio in place of an audio corresponding to the media content;
- and
- outputting the modified media content.
Dependencies are inferred from the claim text.