BibTeX:

@article{IJIRSTV4I11045,
     title={Video Subtitle Generation},
     author={Pratiksha S. Baviskar, Ashwini D. Borse, Radhika D. Bharambe and Aishwarya D. Bakale},
     journal={International Journal for Innovative Research in Science & Technology},
     volume={4},
     number={11},
     pages={149--152},
     year={},
     url={http://www.ijirst.org/articles/IJIRSTV4I11045.pdf},
     publisher={IJIRST (International Journal for Innovative Research in Science & Technology)},
}

Video plays an important role to help people understand and comprehend the information in much easier way, for example movies, songs or video lectures relevant to user. This can be best done by generating subtitles of the video. At present there are some systems which are able to generate only speech to text, not the video to subtitles in efficient way. Also downloading subtitles of any video from the internet is complex process. To generate subtitles of video automatically through software is solution for this. Hence, in this proposed system subtitles can be generated through three different phases namely audio extraction means separating audio from video and converting audio in suitable format if necessary. The second phase proceeds to the recognition of speech contained in the audio, before giving audio for speech recognition audio is divided into number of chunks. The subtitle generation phase generate subtitle file from the recognition results of the previous step. Subtitle generation is the final process to get subtitles as output of video in which a .txt/.srt file is generated synchronized with the input file. This system can help people to remove the gaps of their native language and the auditory problem. It can also help children with word identification, meaning, acquisition and retention, and it can establish a systematic link between written word and the spoken word.

Audio extraction, Audio Segments, Chunks, Speech Recognition, Time Synchronization, Subprocess , Video text merging