brianwhitman

song/identify supported both ENMFP and Echoprint, and AFAIK the Echoprint matching path was exactly the same as is published on Github.

I know at some point we did adapt the Solr end (for example, we removed the N most occurring codes) for speed optimizations.

Many users of Echoprint in the wild have adapted the python matching logic for their use case as well as changed the hash update rate on the codegen. A great modification to watch was Sunlight Labs' "Ad Hawk", which ID'd commercials: https://github.com/sunlightlabs/adhawk

I like this concept, but you need some sort of automated filtering. My first track (because hypem liked it) is a cat purring.

Plug but it's a useful one: run the tracks through the SCAnalyzer http://labs.echonest.com/SCAnalyzer/index.html and filter for speechiness and duration. If you get a SO ID, you'll also know the artist via fingerprinting and you can do more filtering at that level.

psytrance is there, as "psychedelic trance"

we're adding j-core now, thanks for the suggestion!

sxsw is why this is special, we will be adding and changing these over time. It's clear that genres don't have to directly correlate with musical style.

also, code examples: http://musicmachinery.com/2014/01/16/new-genre-apis/

These genres come from people talking about music using whatever organic / natural words they use to describe music. We've done the work to map those into single-term "genres," as it's been shown many listeners appreciate the flat categorization. There are similarities between genres in the API, so you can quickly see which genres sound like others.

http://developer.echonest.com/api/v4/genre/list?api_key=YOUR...

this is going to be a great event, I'm speaking at it too, presenting my old "A Singular Christmas" from 2004 (nee Eigenradio)

http://notes.variogr.am/post/262976984/a-singular-christmas-...

EN (which powers the Rdio create station feature that rolled out recently) has similarity data and popularity data for songs & artists natively.

Popularity of a single song: http://developer.echonest.com/api/v4/song/search?api_key=FIL...

List of songs by an artist ordered by popularity

http://developer.echonest.com/api/v4/song/search?api_key=FIL...

Since we have Rdio in our Rosetta ID space, you can natively use Rdio IDs and get them back in your calls:

http://developer.echonest.com/api/v4/song/search?api_key=FIL...

Analyze your own, it'll be much better when you're doing synchronous stuff like this. Our canonical audio is likely very different in bitrate or time to start.

Yes: you can use Echo Nest Remix in python or do what paul did and pre-load the analysis and do the playback via webaudio. Remix takes care of the chopping at the right bits for you: http://echonest.github.com/remix/

yeah, the new john allison ones put the old logo ones to shame, i hate to see the old style still in the wild.

dear dude in the middle wearing the echo nest t-shirt -- WHO ARE YOU, we'll send you a later edition

hah -- any one of you would do the same faced with an overzealous auto-linker js on IRCCloud, a discussion there about the README.md it points to and access to a corporate credit card. it was very funny at the time, i promise. here's our "announcement": http://blog.echonest.com/post/9332881544/new-pyechonest-on-g...

I really don't think Google built Apple's Mail.app client. Do you have any link or information about this?

The article says "He quoted an NBC spokesman as saying: "Our social media department was actually alerted to it by Twitter and then we filled out the form and submitted it."

I can read this in one of two ways: Twitter (the company) alerted NBC, or Twitter users on the social network Twitter alerted NBC. There's not much clarity there, but obviously the former is scary and confusing and the latter happens all the time.

She has updated her comments with a link to the actual email from Apple:

http://hollylisle.com/apple-made-its-decision-my-turn/commen...

My reading of this is a complete miscommunication. Nowhere in Apple's email does it state they had a problem with content. I really have no idea how she jumped to that conclusion. The very simple and likely explanations are either (1) she did not remove all links or (2) the reviewer did not closely check to see if she removed all links.

Don't see any emails about the content block that she is referring to this post. I see emails about previous issues of her having links to Amazon in her ebooks. I am very curious about this, because I doubt just saying the word "Amazon" can really be an instant rejection -- and a quick search of the iBook store shows tons of books about Amazon itself, things like "How to Self Publish on the Amazon Kindle" et al.

ace, i dug in after the initial read and of course am behind it all. will check it out again after the copy update. good luck!!

dalton, i saw a dear friend support you over my twitter and I clicked but have NO IDEA what this does? Seriously, I am pretty internet savvy but all I read was "feed platform" and how you weren't going to sell my data-- but what data? What is it? you might want to update the landing page a bit :)

https://twitter.com/fascinated/status/223906673457238016

edit: I see i am not the only one. Sorry for the noise, but maybe take it as another vote for more clarity.

I was very upset when I saw that result but a good scientist never shows his bias :(

I do really think that once we get better at "artist evolvement" (separating Pink Floyd into two or three separate artists as they had very distinct phases) the PF signifier will drop. I only listen to Syd and "It Would Be So Nice" era PF and definitely am not a Romney booster.

Maybe, would be cool to try it on location data! As I stated in there, we only used TPs that had US set as location, so the data will be very US-focused.

It's actually a "manifest" -- a list of things that are included (well, should be included) -- in any hack event.

I disagree with this -- i was a very heavy Napster user in 99 and am a very heavy Spotify user (and, NB, they are a customer) today. Obviously it's a fun angle for a SXSW talk, but:

- The "depth of catalog" is actually incorrect -- Spotify has far far more songs than Napster did (you can see in that screenshot even, most logins/servers hit less than 1m songs totally available, and of course those are just total indexed, in reality almost 50% of downloads would not be available.) Yes, you could find niche stuff on Napster-- as a musician in 1999 I would make sure all my stuff was available, pre-release, demos, etc. But we have Soundcloud for that now, so...

- The discovery on Napster was non-existent. You could browse through a users' collection, the same way you can browse through playlists today. But the only entry into anything was a search box that only looked at ID3v1 data and filenames. There's been amazing leaps and bounds in discovery since then, and it's very clear by the #s that it's what people wanted -- a guided (radio, playlist) experience over a wild west single song retrieval thing.

- Napster was stupid bad at search. There obviously was no catalog resolution and the quality of the results was abysmal. I am pretty sure it was a substring match, for one, and then there was the bad metadata, fake songs, later on a huge spam / "SEO" problem.

- Not going to get into speed, because it wasn't Napster's fault, but even back then it was far easier to get music elsewhere other than Napster if possible. Ratio FTP sites, hotline, and of course bubblecruft startups building customer bases by selling new CDs for $4. It was very clear at the time even that the distributed nature of Napster was a liability, not a promise, as all the single-server solutions were far more convenient and reliable. But this was not their fault and of course their success inspired everything after it.

go make an app with another label's content, let me know what you think satire means then

http://developer.echonest.com/sandbox/emi/faq.html

more on the sandboxes: http://blog.echonest.com/post/12273084434/emi-announcement

developer getting started guide: http://developer.echonest.com/sandbox/emi/guide.html

Use Safari. The video doesn't seem to be loadable in any other browser. It WFM in Safari and iOS Safari. Other browsers say "Check back soon."

Right, ISRC is somewhat useful for glue but is not in wide enough use that it covers the world of music. It also reflects "recordings" not "songs" which actually cause a lot of resolution issues (radio edits, clean vs. explicit and etc.) It also does not help anyone resolve artist names like "The The" when their stopword list turns that into an empty query :)

direct link to webapp: http://searchformusicbydrawingapictureofit.com/

Yes-- i pay $250/mo on my plan (international data & etc) and also bought the iPhone4 subsidized day 1, and my message says I am eligible for an upgrade now.