"The majority of user-generated video content online is still inaccessible to people like me," Harrenstien said via the official Google Blog.
Harrenstien says the system, which combines automatic speech recognition with YouTube's current caption system, is not perfect, but that it will "continue to improve with time".
Additionally, users can upload a transcript of their video and Google auto-timing algorithms will match the text to the words on screen as they are spoken.












