Generating Subtitle Using Speech to Text

Abstract

Even though there are many voice recognition software’s such as Dragon Dictation, Naturally Speaking, Windows Speech Recognition still video players do not support voice recognition or voice-to-text either in online or offline. Therefore, in this project it mainly focuses on adding subtitles offline via a specific media player to a movie/video. Subtitles are displayed in English according to the movie/video in a text format, therefore the user can read the subtitles easily though the movie is in another language. And these subtitles include every sensitive noise other than speech such as door slamming, inhaling and exhaling etc. People with hearing issues and people how can’t understand other languages may find hard times while watching a movie without subtitles. Thus, this project will help them to understand the content without any issues. This project is about generating subtitles in English for a specific media player. This will help the people with hearing disabilities and also it will help the people who can’t understand other languages. This will generate subtitles in English, which is the global language where most of the people can understand. User-friendly subtitles are generated which are readable and in a standard quality. Subtitles are displayed in a block where the user will be able to read and understand the content easily even though the video is in a foreign language.