|
|
Subscribe / Log in / New account

Announcing Echoprint

The Echoprint project has announced its existence and initial release of code and data. "The Echo Nest has been focusing on a crucial component of the oncoming music cloud for some time: we spend a lot of time and engineering resources on music resolving. This extends from mapping a query for a band name to its ID, to uncovering mentions of songs on blogs, to identifying the song in an audio stream without any metadata - otherwise known as fingerprinting. The Echo Nest's existing fingerprint technology, 'The Echo Nest Musical Fingerprint' aka ENMFP, has been in wide use privately and via our API for 18 months. Today we are unveiling a new fingerprint technology called 'Echoprint,' whose main feature is its complete openness - everything from the program to analyze the audio to the server and data to make the match are available for anyone to use, under a permissive open source license, for free."

to post comments

Announcing Echoprint

Posted Jun 23, 2011 16:08 UTC (Thu) by lolando (guest, #7139) [Link] (6 responses)

The open-source-ness of the license is debatable. The obligation to send new data back to Echoprint would fail the "desert island test" that's used by Debian for checking compliance with the Debian Free Software Guidelines (which are almost exactly the Open Source Definition).

I nevertheless applaud the idea, and hope that this "omission" is only temporary and will cease to be in effect once some critical mass has been attained.

Announcing Echoprint

Posted Jun 23, 2011 17:51 UTC (Thu) by cworth (subscriber, #27653) [Link] (1 responses)

> The open-source-ness of the license is debatable.

I assume you're referring to the license of the data they are sharing here.

As for the code, the code generator is being distributed under the MIT license and the server is being distributed under the Apache license.

So it looks to me like all the necessary code is available under DFSG-free licenses. And new services could be started with various licenses for the data itself.

-Carl

Announcing Echoprint

Posted Jun 23, 2011 19:17 UTC (Thu) by lolando (guest, #7139) [Link]

> I assume you're referring to the license of the data they are sharing here.

Yes, my bad, I should have been more precise. Hower, one could argue that the license of the actual code may be less relevant than the one for the dataset. If the algorithm is public, then the code can be reimplemented in a compatible and interoperable way. But if we have several datasets under incompatible licenses, there's a networking effect if only one dataset can be under use at any one time. There could, however, be an alternative, clean-room dataset under a license that doesn't fail the "desert island" criterion; if the clients are made to query several data sources, then the initial dataset becomes less important indeed (as long as there's no leakage of data).

"Desert Island" test

Posted Jun 30, 2011 14:01 UTC (Thu) by stevem (subscriber, #1512) [Link] (3 responses)

Please don't advertise the "desert island" test as something that Debian as a whole believes in. It's just a thought experiment and a lot of Debian developers don't accept its validity.

"Desert Island" test

Posted Jul 5, 2011 15:17 UTC (Tue) by nye (subscriber, #51576) [Link] (2 responses)

>Please don't advertise the "desert island" test as something that Debian as a whole believes in. It's just a thought experiment and a lot of Debian developers don't accept its validity.

I've never really thought about it before, but it sounds on its face like a good idea. What are the objections to it?

"Desert Island" test

Posted Jul 5, 2011 15:35 UTC (Tue) by mjg59 (subscriber, #23239) [Link]

It excludes various licenses that have traditionally been thought of as suboptimal but free.

"Desert Island" test

Posted Jul 5, 2011 15:54 UTC (Tue) by stevem (subscriber, #1512) [Link]

Exactly because it's just a thought experiment - see http://people.debian.org/~bap/dfsg-faq.html for it and the other two "tests" that some people seem to find useful.

In my opinion all three of these tests are broken precisely because they're trying to apply hard tests to a license. This is explicitly not in the spirit of the DFSG.

Announcing Echoprint

Posted Jun 23, 2011 16:09 UTC (Thu) by clint (subscriber, #7076) [Link] (1 responses)

How does it compare to acoustid/chromaprint?

Announcing Echoprint

Posted Jun 25, 2011 15:43 UTC (Sat) by dr@jones.dk (subscriber, #7907) [Link]

Without being an expert in the field, I was told that echoprint tracks patterns for _similar_ music,whereas chromaprint tracks patterns for _same_ music.

Echoprint data makes it possible to auto-generate a playlist. Chormaprint makes it possible to identify a tune even if degraded by lossy compression.


Copyright © 2011, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds