Subtitle processing method, device and storage medium

Abstract

Embodiments of the present invention provide a subtitle processing method, device, and computer-readable storage medium. Wherein the subtitle processing method includes: extracting the first subtitle text from each frame image of the video; adding punctuation in the first subtitle text, so as to connect the first subtitle text through the punctuation to obtain the second subtitle text ; Segmenting the second subtitle text to generate an article transcribed from the video. In the embodiment of the present invention, punctuation is added to the sentences in the subtitles to connect the subtitles, and the connected subtitles are segmented to finally generate an article with coherent semantics, smooth flow and richer information. The editing accuracy of this method is high and can avoid the subjective deviation of manual mode; at the same time, this method has higher timeliness and saves labor cost and time cost.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a subtitle processing method, device and computer-readable storage medium. Background technique [0002] When transcribing articles based on multimedia content, usually the video sources used only have subtitles that do not contain punctuation and no segmentation information. If the subtitles are simply connected when the article is automatically generated, it will be difficult to read, and there will be no semantic segmentation, which will greatly affect the user's reading experience. [0003] At present, in the process of multimedia transcription, it is more common to use manual editing to connect sentences and segment original text data, but such manual methods mainly have the following defects: (1) partial subjectivity, for In an artificial way, different subjective biases often affect the final effect of text connection and segmentation. (2) Limitation. Due to...

AI Technical Summary

Problems solved by technology

If the subtitles are simply connected when the article is automatically generated, it will be difficult to read, and there will be no semantic segmentation, which will greatly affect the user's reading experience

[0003] At present, in the process of multimedia transcription, it is more common to use manual editing to connect sentences and segment original text data, but such manual methods mainly have the following defects: (1) partial subjectivity, for Artificial way, different subjective biases often affect the final effect of text connection and segmentation

(2) Limitation, due to limited manpower, it is often impossible to connect and segment all texts

(3) Complex and inefficient, manual retelling of text, high cost and low efficiency

(4) The accuracy is poor, the manual editing method is prone to errors, and the accuracy cannot be guaranteed

Images