January 27, 2006

Biznology Blog by Mike Moran

« Replay of Yesterday's Interview on wsRadio.com | Main | More on Audio Search »

A New Way to Find Podcasts

If you're using podcasts to get your message to prospective customers, you should know about a whole new way for people to find your content. A new podcast search engine offers a breakthrough that may make podcasts easier to find than ever.

Up until now, podcast search was no better than image search, which depends on searchers using the words around the image file, or the name of the file itself. The search engine does not know that it's a picture of a zebra—it is counting on the image being named "zebra.gif" (for example). Podcasts, until now, were similarly second-class content, compared to first class Web pages (and blog entries) that can be found by entering any word found on that page.

A new search engine, PODZINGER, takes a new approach, using speech recognition technology to convert podcasts (or any audio) to text. Speech recognition software can "listen" to audio and identify most of the words spoken, converting it to plain computer text, the same as any Web page. Once converted, any text search engine can find that audio file based on any word spoken.

PODZINGER is a neat tool that can help you find podcasts, but search marketers are waiting for mainstream search engines to offer speech recognition—when Google and Yahoo! can perform this trick, the average searcher will start to find podcasts. The development will cause a huge increase in podcast usage. You may even see it happen this year.

Posted by MikeMoran at January 27, 2006 9:12 PM

Trackback Pings

TrackBack URL for this entry:
http://www.mikemoran.com/mt/mt-tb.cgi/79

Comments

I tried Pzinger. It was clever; I'm not sure if there is anything else out there that does what it does. podscope is an AV search engine but not focused on podcasts. An observation - the transcription snippits appears to be 50% accurate. Do you think this is acceptable and do you think a full transcription is necessary?

Posted by: Clif at January 27, 2006 10:10 PM

Acceptable is in the eye of the beholder--what I think is important is that we are moving from having no ability to find audio using its contents to suddenly having some ability. I think that makes a world of difference and I think that Yahoo! and Google will be doing it soon. Granted, there are inaccuracies, but I think going from a black box to a gray box is significant progress, even though we all wait for the white box.

Posted by: Mike Moran at January 28, 2006 7:06 AM

Mike, seems there are some folks at IBM (http://www.pcmag.com/article2/0,1759,1916107,00.asp?kc=PCYH104039TX1B0000663) who think effective speech recognition is just around the corner. I think we need to nail transcription accuracy before we explore spoken translation. Are these guys high or are they for real?

Posted by: Clif at January 30, 2006 10:29 AM

I know David Nahamoo and he is very well-respected. It is undoubtedly the case that better speech recognition technology will improve any application, inluding search. I think that the IBM technology would definitely have a big impact on quality when it is applied to search and also believe that even the quality available today has value.

Posted by: Mike Moran at January 30, 2006 11:06 AM