公开(公告)号：US20240371370A1

公开(公告)日：2024-11-07

申请号：US18573404

申请日：2023-05-31

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xin ZHENG ,  Lelai DENG ,  Keyu CHEN

IPC: G10L15/187 ,  G10L15/04 ,  G10L15/18 ,  G10L25/57 ,  G11B27/036 ,  G11B27/34

Abstract: The present disclosure relates to a subtitle generation method, a subtitle generation apparatus, an electronic device, a storage medium and a program. The method includes: extracting audio data from a video to be processed, and performing speech recognition on the audio data to acquire text data corresponding to the audio data; acquiring a plurality of segmentation positions of the text data determined based on syntactic analysis, and acquiring pronunciation object information and timestamp information of audio segments corresponding to characters comprised in the text data; segmenting the text data to acquire a plurality of text segments according to the plurality of segmentation positions, the pronunciation object information and the timestamp information of the audio segments corresponding to the characters, wherein audio segments corresponding to characters in a text segment belong to a same pronunciation object, and a duration of a blank segment in the audio segments corresponding to the text segment is less than a preset duration; merging the plurality of text segments according to semantics of the text segments and the timestamp information of the audio segments corresponding to the characters to acquire a plurality of merged segments which have smooth semantics and meet a preset requirement of single subtitle length; and generating subtitle data corresponding to the video to be processed according to the plurality of merged segments.

公开(公告)号：US20240281938A1

公开(公告)日：2024-08-22

申请号：US18571611

申请日：2022-09-09

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Feng ZHOU ,  Junyue CAO ,  Ruiqi XIA ,  Linhao YU ,  Tao HUANG ,  Liyu LIANG ,  Keyu CHEN ,  Kaibo CHU

IPC: G06T5/77 ,  G06V10/25

CPC classification number: G06T5/77 ,  G06V10/25 ,  G06V2201/07

Abstract: The present disclosure provides a video processing method and apparatus, an electronic device, and a medium, and the method includes: acquiring a to-be-erased region including a to-be-erased object in each target video frame of a to-be-processed video; acquiring, for a single target video frame, acquiring, from another target video frame other than the target video frame, a target region that corresponds to a to-be-erased region of the target video frame and does not include the to-be-erased object; filling pixels of the target region into the to-be-erased region of the target video frame, to erase the to-be-erased region of the target video frame; and in response to an unerased region existing in the to-be-erased region of the target video frame, predicting pixels of the unerased region according to the target video frame, and filling the unerased region according to the predicted pixels to erase the unerased region.