VIDEO TRANSLATION METHOD, SYSTEM AND DEVICE, AND STORAGE MEDIUM

• Main Authors: HU, Yuzhen, WANG, Lunji, HAN, Lanqing, YE, Juejie, CHENG, Qiuxi, LI, Jiaxiong, LI, Quan, ZHU, Jie
• Format: Patent
• Language: Chinese; English; French
• Published: 02.06.2022
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

A video translation method, system and device, and a storage medium. The method comprises the following steps: obtaining video data; performing voice segmentation on the video data to obtain a voice segment and a video segment corresponding to the voice segment (S1); performing voice recognition on the voice segment to obtain a first text, and translating the first text to obtain a second text (S2); obtaining a synthesized voice according to the second text, and adjusting the synthesized voice and the video segment corresponding thereto, such that the synthesized voice matches with the video segment (S3); and detecting and adjusting a lip shape in the video segment, such that the lip shape synchronously matches with the synthesized voice (S4). By means of the method, the function of automatically translating a video is realized, an audio of a target language sound can be generated, a video having the sound matching the lip shape is generated, the communication obstacle between different languages is solved, m