How can you automatically detect that from a video? And if instead of automatically detecting it, you just let the users tag the video, why does text search not work? Finally, even if they manage to get a useful video search working, why do they need Youtube for it, when they can crawl the web for video?
Google is working on this- One theory is that part of why they are working on Goog411 is to increase their voice reco engine, so that they can apply it to Video and Audio search.
Google hired several engineers away from Nuance (one of the leaders in voice recognition), and they're working hard on growing their development there.
How can you automatically detect that from a video?
that is the point I'm trying to make. it is not possible today, I guess it will be possible in future.
how much can you tag? and who will do all the work of tagging? it has to be automated, like text search. video search is going to be much more difficult than text, and G has tons of videos to mine and refine algos.