Multimedia Search Tech Provider Nexidia Unveils Public Demo on Atlanta TV Station Site
A multimedia search product we’ve mentioned many times on ResourceShelf is Nexidia.
Nexidia is a multimedia search company out of Georgia that creates a searchable corpus (words and phrases) but does it unlike other products that provide transcript (every word spoken) search.
Nexidia takes words and phrases and breaks them down into phonetic sounds (phonemes) and then indexes them. This allows for faster indexing (65x real time), reduced computer power requirements, and, what’s most important, more precise indexing and search retrieval.
Three other ways to search video/audio are speech-to-text, closed captioning, and metadata. Of course not every show, conference, etc., offers closed captioning and those of us with tools that can transcribe our words to text know it often takes some time and training to get it correct.
About 40 phonemes exist in every language with about 400 in all spoken languages. Trust us, the Nexidia documentation and explanation makes for some interesting reading including this page. We think it’s easy to see how easy and quick an installation could be ready to go. The only negative is that no text transcript is created.
To this point, it’s been difficult to demo Nexidia technology since there haven’t been any public demo sites. Most of their business is with private companies (recording call center chats, for example) and the government.
However, as of today, we have a publicly accessible demo to take a look at with Nexidia. It comes from Channel 11 (WXIA) in Atlanta and allows you to keyword search all of their news programming (no sports) plus some exclusive web footage. Look for the search box in the middle of the page. Of course, don’t forget that this is a beta release.
There are several ways to limit by date range, and note the advanced search page where you can also tell the database within how many seconds you want your search terms to be spoken within each other. For example, within 10 seconds x number of words need to be spoken. Note: You will need Active X installed.
When you find your result(s), click on the link and go precisely to where those words are spoken. Amazing and from what I’ve seen with some very limited testing, very accurate. Results are rated as to how accurate they are versus your search terms.
With the speed and accuracy of indexing and the need not to have to train a speech-to-text tool, we think the day is rapidly approaching when a student can come home from a lecture, plug in their recording device, and within minutes be able to keyword search the material right from their desktop or laptop. Think of all of the other possibilities.
More than worth a look not only for the technology but for the concepts and how this type of indexing might be an example of the future, today.
October 8th, 2006 at 11:53 pm
[...] First, Nexidia (the multimedia engine) and now another product we’ve been writing about for months has released it’s public beta. SkylineGlobe is here! [...]
October 9th, 2006 at 1:48 pm
[...] + Weeks After Microsoft Announces a Video Search Beta, Blinkx Technology Has Been Licensed by Microsoft (via Reuters) No ad cut, straight licensing fee. See Also: Multimedia Search Tech Provider Nexidia Unveils Public Demo on Atlanta TV Station Site [...]
October 16th, 2006 at 8:07 pm
[...] See Also: As noted last week, WXIA in Atlanta (NBC) lets you search news video by creating a network using phonetic sounds. It’s one thing to have the content, it’s another to be able to find it, quickly and easily. [...]
January 5th, 2007 at 8:00 am
[...] 3)Perhaps the most interesting player in this space is Nexidia. This Georgia-based company approaches transcript searching from a different angle. Most others use either speech-to-text or closed-captioning to search on. Nexidia is different. They break the spoken word into phonetic sounds (phonemes, about 40 in the English language) which makes for strong accuracy (not perfect however), less computing power and less “training” for jargon and other words. Nexidia has a strong presence in the call center and government marketplaces. Another strength is that it will work with most languages. In the Fall of 2006, Nexidia launched a demo site using video from a tv station in Atlanta. [...]
January 10th, 2007 at 8:13 pm
[...] I also agree 100% with Paula that video (and audio) will continue to be a big deal. The question is, will user-contributed video (the jump-off the roof type of stuff) continue on the run it’s currently on or if it’s just a fad, will the fad begin to slow down? Regardless, video and audio from major networks, local stations, universities, think tanks, etc. will continue to grow. As some of you have noticed, we are regularly linking to interesting webcasts on ResourceShelf. Of course, multimedia search has been part of the information professionals toolbelt for years. Services like TVEyes.com, Critical Mention, and ShadowTV are three examples. We’ve also written another company, Nexidia, that is doing some very interesting work in this area. We wrote about them here with a link to a demo from a tv station in Atlanta. [...]
January 26th, 2007 at 4:35 pm
[...] Social networking and personal recording studio aside, the technology, speech and voice recognition, is something that we’ve posted about in the past on RS. It’s technology that will become common place over the next few years as we speak (or sing) our searches. It’s also going to be used (and is being used) to make spoken word content searchable. An example is Nexidia. To this point their technology has been used in call center and government locations. Unlike other technology, Nexidia breaks the spoken word down into phonemes/phonetic sounds. It makes for faster and more accurate indexing. No dictionary to develop, jargon to consider, or closed captioning to worry about. It also works with most languages very easily. A few months ago we posted an item about Nexidia along with a link to a demo you can use from an Atlanta television station. [...]
February 27th, 2007 at 12:46 am
[...] + Nexidia, also online for a couple of years, offers phonetic searching (phoneme) search of each word spoken in a video or audio. In October, we posted about their first public demo available here from an Atlanta television station. [...]