Providing subtitle for video content
AssigneeVoyagerX, Inc.
InventorsHyeonsoo OH, Sedong NAM
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to systems and methods for providing subtitle for a video. The video's audio is transcribed to obtain caption text for the video. A first machine-trained model identifies sentences in the caption text. A second model identifies intra-sentence breaks with in the sentences identified using the first machine-trained model. Based on the identified sentences and intra-sentence breaks, one or more words in the caption text are grouped into a clip caption to be displayed for a corresponding clip of the video.
Claims2
A method of providing subtitle, the method comprising:
- providing a first translated sentence in a second language as a translation of a first sentence spoken in a video in a first language;
- segmenting the first translated sentence into a clip text;
- and determining a display period for displaying the clip text as a subtitle while playing the video.
A method of providing subtitle, the method comprising:
- obtaining a first translated sentence in a second language corresponding to a first sentence spoken in a video in a first language;
- identifying a first clip text ending with a first word contained in the first sentence based on an intra-sentence break probability for the first word among words contained in the first sentence in the first language;
- and
- determining a second language clip period for displaying a first translated clip text of the first translated sentence as a second language subtitle,
- wherein the second language clip period corresponds to a first language clip period determined for the first clip text, and
- wherein the second language clip period is determined based on the first language clip period regardless of whether the first word ending the first clip text corresponds in meaning to a last word of the first translated clip text.
Dependencies are inferred from the claim text.