Sign up for the FREETell Membership and receive benefits that include the digital edition of Tell Magazine sent straight to your inbox, product giveaways, coupons and much more!
There can’t be many people who have been on the internet, and not also been on YouTube, and the home video craze has really caught on. This is both good and bad: it makes videos more accessible but leaves the door open for happy slapping idiots trying to make a name for themselves. And recently another problem has arisen, it’s starting to get a bit too big.
With a reported 13 hours of video being uploaded every minute it is becoming increasingly difficult to find the video that you want, however specific you are. So new techniques are needed, and there are plans to use voice recognition to automatically convert the words into metadata which in turn is embedded in the video meaning key words can be searched for with increased effectiveness. It also means, if you know what video you are looking for, you can directly quote from the video and thus find it easily.
Admittedly the grainy videos with poor sound quality would make this impossible to run without some kind of checking, so presumably this would add time to the upload process as they would have to check the recognition is correct. Perhaps a system by which the speech is typed in by the person uploading would be more effective. However for speeches (presidential candidate ones are currently using this) it is great, and if they can get it to work it shows great promise for the future.
There can’t be many people who have been on the internet, and not also been on YouTube, and the home video craze has really caught on. This is both good and bad: it makes videos more accessible but leaves the door open for happy slapping idiots trying to make a name for themselves. And recently another problem has arisen, it’s starting to get a bit too big.
With a reported 13 hours of video being uploaded every minute it is becoming increasingly difficult to find the video that you want, however specific you are. So new techniques are needed, and there are plans to use voice recognition to automatically convert the words into metadata which in turn is embedded in the video meaning key words can be searched for with increased effectiveness. It also means, if you know what video you are looking for, you can directly quote from the video and thus find it easily.
Admittedly the grainy videos with poor sound quality would make this impossible to run without some kind of checking, so presumably this would add time to the upload process as they would have to check the recognition is correct. Perhaps a system by which the speech is typed in by the person uploading would be more effective. However for speeches (presidential candidate ones are currently using this) it is great, and if they can get it to work it shows great promise for the future.
To see this in action go to http://www.youtube.com/youchoose where you can search for words used in candidates speeches.
Related Posts