Remember Google’s captions for Google Video and YouTube? Yes those that considerably aided the deaf and hearing impaired. These were later incorporated with multiple caption tracks, improved search functionality and even automatic translation. Stepping it up with yet another milestone, the official Google blog makes public machine-generated automatic captions.
Ever since captions were originally launched in Google products, the company claims to have witnessed a surge in the number of videos that have been captioned. The company alludes that a growing number of users are now becoming aware of the usefulness of captions. Now with machine translation, the company hopes that besides the deaf and hearing impaired even people around can benefit from this service.
The machine translation permits users to gain access to video content in any of 51 languages. Besides, captions could also help to enhance search along with allowing users to jump to precise parts of the videos that they could be looking for. Automatic captions address the issue of scaling faced by YouTube users. Google’s automatic speech recognition (ARS) technology has been combined with the YouTube caption system for this very purpose.
Taking maximum advantage of both Google and YouTube functions, automatic captions or auto-caps for short use the same voice recognition algorithms in Google Voice to render automatic captions for video. Though the captions may not always be perfect the company hopes that they are as helpful when they’re off.
Besides, automatic captions, Google is also releasing automatic caption timing, or auto-timing that should make it significantly effortless for users to generate captions manually. With this novel feature, users no longer require a special expertise to create their own captions in YouTube. To go about it, users simply have to create a text file with all the words in the video. Google will then utilize its ASR technology to figure out when the words are spoken and create captions for the video. This attribute should also prove beneficial to video owners who may be short of time or resources when creating professional caption tracks.
Both features will be available in English by the end of the week. As part of the initial launch, auto-caps are only visible on a handful of partner channels including UC Berkeley, Stanford, MIT, Yale, UCLA, Duke, UCTV, Columbia, PBS, National Geographic, Demand Media, UNSW and most Google & YouTube channels. Auto-timing is however rolling out globally for all English-language videos on YouTube.
No comments:
Post a Comment