January 12, 2006

Podcast Search Engine Launched - Driven by Speech Recognition Software

The next generation of a podcast search engines was shared on LISNews.org. PODZINGER allows a user to search a podcast for the exact occurrence of a word or phrase. The user can than play the entire podcast or can click on any of the words in the transcript to start replay at that point.

For example, I searched for "chemical engineering" and sorted the results by relevancy. I was able to jump right into a Science Friday show from National Public Radio (NPR) and hear a chemical engineering professor from MIT get introduced; or listen to a podcast created during the National Chemistry Week of the American Chemical Society.

Once a user conducts a search, they can subscribe to the search parameters by RSS and get new results as they arrive. Users can subscribe to the podcast web site's xml feed, download the entire contents of the single podcast, or subscribe in iTunes or Yahoo.

If you create podcasts, you can add the search functionality to your web site, and also register your podcast feeds for others to see.

[About PODZINGER]

What is PODZINGER?
PODZINGER is a podcast search engine that lets you search the full audio of podcasts just like you search for any other information on the web.

What is the difference between PODZINGER and other podcast search sites?
Most podcast search sites provide directories of podcasts by subject, category, or they search only the metadata provided by the creator of the podcast. PODZINGER takes search a step further by searching the spoken words inside the podcast in order to find more specific and relevant results. The text-based search results include snippets from the audio to help you figure out if the result is relevant. You can even click on the words to listen to the audio from that point.

How does PODZINGER work?
PODZINGER creates a text index of the audio data, using the industry's leading speech-to-text technology from BBN Technologies, to enable search within a podcast, not just within the metadata.

What formats and languages are supported by PODZINGER?
PODZINGER will index, search and reference podcasts in English (language tag in RSS file must begin with "en"), formatted as MP3 or WAV files.

Categories

Trackbacks

Trackback URL for this entry is: http://blog.case.edu/bcg8/mt-tb.cgi/5222

Alternative Trackback Sources: | Google It! | Technorati | Bloglines

Comments

Posted by Sharon
Posted on July 13, 2008 01:56 AM

Nice good blog!