A music search engine that uses a novel technique to classify songs,will go into beta this week.

I wrote about the system a few months ago. It was designed by researchers from the University of California, San Diego, including assistant professor Gert Lanckriet. The researchers have trained the search using information contributed by Facebook users, via an application called HerdIt. The goal is to train the system to tag songs automatically--using statistical analysis applied to the waveform patterns that represent each song:

About 90 percent of the time, Lanckriet says, the system identifies patterns that are ordinarily hidden. For example, the patterns that identify a hip-hop song might include a typical hip-hop beat, but also elements that the listener wouldn't recognize as a pattern within the song. "On average, these automatic tags predict other humans' [tags] pretty much as accurately as a given human person can do," Lanckriet says.[...] He envisions a system that could take an unfamiliar song--from an independent band, or even something recorded in a user's garage--and then analyze it on the fly and suggest appropriate tags and similar music.

I'm looking forward to trying it out. See the video below for a more detailed explanation of the project.

Bing now shows real-time status updates from Twitter.

* Updated at 6:55 PM ET.

In two separate, non-exclusive deals, Microsoft will partner with Facebook and Twitter to show status updates in its search site, Bing. Microsoft officially announced the deals at the Web 2.0 Summit today.

While rumors of the Microsoft-Twitter deal have been circulating for a few weeks, integrating Facebook updates is a surprise twist, although not entirely unexpected, given Microsoft's $240 million investment in Facebook two years ago. Google is said to be in talks with Twitter and Facebook as well.

*(It didn't take Google long to respond. An official blog post reveals that the company has also signed a deal to index real-time information from Twitter).

Twitter has been gaining notice as a valuable source of real-time information. For example, news often breaks on Twitter before hitting major media outlets and well before showing up in search engines. In January Yahoo announced TweetNews, which ranks Yahoo News stories based on Twitter posts.

The integration seems to be a win-win situation: social networking sites will presumably help search engines capture trending news topics more quickly, while the search engines can offer needed revenue streams to the social networking sites and help solidify their legitimacy. It also makes it harder for businesses to ignore social media: with the integration, having Facebook and Twitter accounts can also help a company gain prominence in the much-coveted top spots on search results.

The new Wolfram Alpha App for the iPhone.

The word "egonomics" was a typographical error in an email. The Wolfram Alpha people meant to say "ergonomics" in describing the new iPhone app for the Wolfram Alpha computational knowledge engine, the search-like tool that can run nearly any calculation and cough up interesting graphics on a growing, but still limited, range of subjects.

But at $50 for the app, it seems like an appropriate slip indeed.

Already you can use Wolfram Alpha for free online. (Read my feature on it here.) And you can even use a version optimized for the iPhone interface. Despite this, usage of the site has not taken hold in the popular imagination, with only about 200,000 to 300,000 users daily.

The app gives you a calculator-like interface with various function keys, to help you fill out equations in the search field, and some other improvements. But who would pay $50 for this? The answer: scientists and engineers and other specialists. Indeed, Wolfram Alpha says, in justifying the price: "It's less than half the cost of a less fully-featured graphing calculator. That's how we got to the price."

But the guiding goal of the engine's brainchild, the physicist Stephen Wolfram, was to "make all systematic knowledge immediately computable and accessible to everyone." The fact that the company's first iPhone app is a pricey online calculator for geeks represents more of a retrenching back to the original product produced by Wolfram Research---the wonderful specialty science and engineering software package, Mathematica. The task of engaging a broader audience may have to fall to third-party developers.