Tuesday, September 16, 2008

Google Audio Indexing

Google's efforts to improve video search by using speech recognition technology started to become visible in July, when Google launched a gadget for searching inside the political speeches from YouTube. The gadget has been expanded into a new service called GAudi (Google Audio Indexing), which is now available at Google Labs.

"Google Audio Indexing is a new technology from Google that allows users to better search and watch videos from various YouTube channels. It uses speech technology to find spoken words inside videos and lets the user jump to the right portion of the video where these words are spoken. (...) Political videos and election materials are a special case of broadcast news content, a domain that has received a lot of academic and industry attention and is known to perform well," explains the FAQ.

The interface is attractive because you can find all the mentions of your keywords and go directly to the appropriate sequence. And if you find an interesting video, there's another search box that lets you search inside that video.

Google's technology is far from being perfect, so you'll find many mistakes. In the video "Barack Obama on the 40th Anniversary of the Prague Spring", "Czechoslovakia" is incorrectly detected as "tech also but there", "free" is replaced by "forty" and there are many other mistakes.


{ Thanks, Kevin and Pat. }

No comments:

Post a Comment