The invention discloses a technology for realizing real-time
subtitle overlay during a video call and applications of the technology. The technology comprises
subtitle software, and comprises the following steps: S1, a voice
recognition algorithm, namely, through a
machine learning
algorithm, capturing audio data in a video in real time, and converting the audio data into language data with practical meaning; S2, a character converting
algorithm, namely, carrying out
algorithm processing on the acquired
voice data so that character information is obtained through converting in real time; S3, asubtitle display algorithm, namely, carrying out real-time character-by-character or word-by-word display on the character information; S4, an automatic
sentence punctuating algorithm, namely, analyzing an audio file, so that the starting and pausing points of one
sentence are acquired; and S5, a character and audio /
video overlay method, namely, directly displaying characters to a video interfacein an
overlay manner, so that video captions are formed, wherein the video interface does not assign the display positions of the character subtitles. Through the technology for realizing real-time
subtitle overlay during a video call and the applications of the technology, after the complete
sentence is acquired, all the displayed characters can be updated according to the meaning of the complete sentence.