Ronnie05's Blog

Google Audio Indexing: Empowering Media Democratization

Posted in Internet and Search by Manas Ganguly on October 28, 2009

YouTube is associated with the democratization of media. In real terms it is the Google in Web Media. However, there are times and moments when a user would like to search for a particular reference in a speech and GAUDI is Google’s search solution to enable search for words on media files. The excitement never stops at Google it seems.

Google’s mission is “to organize the world’s information and make it universally accessible and useful”. As more video content is being created everyday, Google Audio Indexing (Gaudi) 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. Google Audio Indexing thus makes it easier for people to find and consume spoken content from videos on the Web.

Google Audio Indexing is a showcase for speech technology. 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. By making the technology available to a wide audience, Google offers a useful service to the consumers of video and media feeds.


Google already has Google Elections Video Search gadget which is more US centric information and is very instrumental in culling information that describes the views, actions and platforms of the two presidential candidates. Both, Google Audio and Google Elections Video Search gadget use the exact same underlying technology. While, the scope of the Google Elections Video Search gadget is restricted to the US election. The aim of Google Audio Indexing on Google Labs is broader and the US election is just a first step. Thus Google Elections Video Search is an experiment platform where Google can learn what features make the best user experience for people looking for spoken content on the Web. To put it in context, Elections Video Search is a precursor to GAUDI.

Google Audio Indexing uses speech technology to transform spoken words into text and leverages the Google indexing technology to return the best results to the user. The returned videos are ranked based — among other things — on the spoken content, the metadata, the freshness. The gadget periodically crawls the YouTube political channels for new content. As soon as a new video is uploaded to YouTube, it is processed by the system and made available in the GAUDI index for people to search.

Google Audio Indexing searches only those videos uploaded on the YouTube political channels. If a video is on the YouTube political channels, it will be in the index. Candidates control the video content released to the public using Google Audio Indexing technology by controlling the content they upload to YouTube channels. That is a limited scope currently, but it wont be long before Google democratizes the use over the whole YouTube Gamut!

Tagged with: ,
%d bloggers like this: