Site Map - skip to main content - dyslexic font - mobile - text - print

Hacker Public Radio

Your ideas, projects, opinions - podcasted.

New episodes Monday through Friday.


hpr2016 :: Echoprint

I share what I've learned about the Echoprint music identification system

<< First, < Previous, Latest >>

Host Image
Hosted by laindir on 2016-04-25 is flagged as Clean and is released under a CC-BY-SA license.
Listen in ogg, spx, or mp3 format. | Comments (2)

Ken's message asking about programmatically checking for the intro and outro: http://thread.gmane.org/gmane.network.syndication.podcast.hacker-public-radio/1039

The Echoprint website: http://echoprint.me

Codegen source code: https://github.com/echonest/echoprint-codegen

Echoprint - An Open Music Identification Service: https://www.ee.columbia.edu/~dpwe/pubs/EllisWP11-echoprint.pdf

Server source codehttps://github.com/echonest/echoprint-server


Comments

Subscribe to the comments RSS feed.

Comment #1 posted on 2016-04-25T19:52:21Z by Ken Fallon

Thank you Thank you Thank you Thank you

I would have gotten lost at the first hurdle.

Although you may not be able to determine if the the music was the HPR theme or not, could you determine if there was music in a section at all ?

Say if we cut the first 3 minutes from the front and end of a episode, could it check if there was music in there ?

Thanks,

Ken.

Comment #2 posted on 2016-05-23T16:36:49Z by laindir

Late

Quite behind on my listening, so I didn't even think to check for comments until I caught the community news show just now (just caught up to my episode last night). Frankly, I'm way over my head. My very limited understanding of the fingerprint is that it's just a timestamped list of transitions between sounds. I don't know nearly enough about signal processing generally, nor about how Echoprint encodes those transitions specifically, to even speculate how one would begin to distinguish between music and speech.

Leave Comment

Powered by Comment Script