Posts Tagged echonest
Yesterday, I upgraded the Infinite Jukebox to make it less likely that it would get stuck in a section of the song. As part of this work, I needed an easy way to see the play coverage in the song. To do so, I updated the Infinite Jukebox visualization so that it directly shows play coverage. With this update, the height of any beat in the visualization is proportional to how often that beat has been played relative to the other beats in the song. Beats that have been played more have taller bars in the visualization.
This makes it easy to see if we’ve improved play coverage. For example, here’s the visualization of Radiohead’s Karma Police with the old play algorithm after about an hour of play:
As you can see, there’s quite a bit of bunching up of plays in the third quarter of the song (from about 7 o’clock to 10 o’clock). Now compare that to the visualization of the new algorithm:
With the new algorithm, there’s much less bunching of play. Play is much more evenly distributed across the whole song.
Here’s another example. The song First of the Year (Equinox) by Skrillex played for about seven hours with the old algorithm:
As you can see, it has quite uneven coverage. Note the intro and outro of the song are almost always the least played of any song, since those parts of the song typically have very little similarity with the rest of the song.
Here’s the same song with the new algorithm:
Again, play coverage is much more even across all of the song outside of the intro and the outro.
I like this play coverage visualization so much that I’ve now made it part of the standard Infinite Jukebox. Now as you play a song in the Jukebox, you’ll get to see the song coverage map as well. Give it a try and let me know what you think.
My Music Hack Day Berlin hack was “Where’s the Drama?” – a web app that automatically identifies the most dramatic moment in any song and plays it for you. I’ve been having lots of fun playing with it … and even though (or perhaps because) I know how it works, I’m often surprised at how well it does at finding the most dramatic moments. Here are some examples:
- When will the Bass Drop – Lonely Island
- Stairway to Heaven – Led Zeppelin
- Doomsday – Nero
- November Rain – Guns N Roses
How does it work? The app grabs the detailed audio analysis for the song from The Echo Nest. This includes a detailed loudness map of the song. This is the data I use to find the drama. To do so, I look for the part of the song with the largest rise in volume over the course of a 30 second window (longer songs can have a bit of a longer dramatic window). I give extra weight to crescendos that culminate in louder peaks (so if there are two crescendos that are 20dB in range but one ends at 5dB louder, it will win). Once I identify the most dynamic part of a song, I pad it a bit (so we get to hear a bit of the drop after the build).
Playing the music – I wanted to use Spotify to play the music, which was a bit problematic since there currently isn’t a way to play full streams with the Spotify Web API, so I did a couple of hacky hacks that got me pretty far. First of all, I discovered that you can add a time offset to a Spotify URI like so:
When this URI is opened in Spotify (even when opened via a browser), Spotify will start to play the song a the 1:05 time offset.
I still needed to be able to stop playing the track – and there’s no way to do that directly – so instead, I just open the URI:
which happens to be the URI for John Cage’s 4’33. In other words, to stop playing one track, I just start playing another (that happens to be silent). The awesome side effect of this is that I’ll be slowly turning anyone who uses “Where’s the Drama?” into experimental music listeners as the Spotify recommendation system responds to all of those John Cage ‘plays’. This should win some sort of ‘hackiest hack of the year’ award.
It was a fun hack to make, and great fun to demo. And now that I have the app, I am no longer wasting time listening to song intros and outros, I can just get to the bit of the song that matters the most.
This weekend I’m at The Music Education Hack in New York City where educators and technologists are working together to transform music education in New York City. My hack, Rock Steady, is a drummer training app for the iPhone. You use the app to measure how well you can keep a steady beat. Here’s how it works:
First you add songs from your iTunes collection. The app will then use The Echo Nest to analyze the song and map out all of the beats. Once the song is ready you enter Rock Steady training mode: The app will show you the current tempo of the song. Your goal then is to match the tempo by using your phone as a drumstick and tapping out the beat. You are scored based upon how well you match the tempo. There are three modes: matching mode – in this easy-peesy mode you listen to the song and match the tempo. A bit harder is silent mode – you listen to the song for a few seconds and then try to maintain the tempo on your own. Finally there’s bonzo mode – here the music is playing, but instead of you matching the music, the music matches you. If you speed up, the music speeds up, if you slow down, the music slows down. This is the trickiest mode – you have to keep a steady beat and not be fooled by the band that is following you.
This is my first iOS hack. I got to use lots of new stuff, such as Core Motion to detect the beats. I stole lots of code from the iOS version of the Infinite Jukebox (all the track upload and analysis stuff). It was a fun hack to build. If anyone thinks it is interesting I may try to finish it and put it in the app store.
Here’s a video:
With all the controversy surrounding Glee’s ripoff of Jonathan Coulton’s Baby Got back I thought I would makes a remix that combines the two versions. The remix alternates between the two songs, beat by beat.
At first I thought I had a bug and only one of the two songs was making it into the output, but nope, they are both there. To prove it I made another version that alternates the same beat between the two songs – sort of a call and answer. You can hear the subtle differences, and yes, they are very subtle.
The audio speaks for itself.
Here’s the code.
My latest music hack is Bangarang Boomerang. It is a web app (runs in Chrome or the latest Safari), that lets you ‘drive’ the Skrillex song. You can freeze-frame the song on a beat, you can make the song go backwards beat by beat, you can advance through the song at double time, or triple time, and set bookmarks to let you easily jump to different sections of the song. It is a rather fun app that lets you feel like a musician, even if you have very little musical talent.
Watch the quick Youtube demo, and then try it yourself: Bangarang Boomerang
I’m at Music Apps Hack Weekend doing my favorite thing: hacking on music. I’ve just finished my hack called Boil the Frog. Boil the Frog is a Spotify App that will create playlists that gradually take you from one music style to another. It is like the proverbial story of the frog in the pot of water. If you heat the water gradually, the frog won’t notice and will happily sit in the pot until it becomes frog stew. With Boil the Frog you can do the same thing musically. Create a playlist that gradually takes your pre-teen from Miley Cyrus to Miles Davis, or perhaps more perversely the Kenny G fan to Cannibal Corpse.
To build the app I built an artist similarity graph of 100,000 of the most popular artists. I use The Echo Nest artist similarity to connect each artist to its four nearest neighbors. To find the path between any two artists I use a bidirectional Dijkstra shortest path algorithm. Most paths can be computed in less than 100ms.
The Spotify Apps API is the perfect hacking platform. You can build a Spotify app that has full access to the vast Spotify music catalog and artwork, along with access to the listener’s catalog. Since the Spotify Apps run in an embedded browser all of your web app programming skills apply. You can use jQuery, make calls to JSON APIs, use HTML 5 canvas. It is all there. Spotify has done a really good job putting together this platform. The only downside is that, unlike the web, it is hard to actually release Spotify apps, but the Spotify team is working to make this easier. I’d love to release Boil the Frog because it is really fun to make playlists that bring you from one music style to another. It is interesting to see what musical neighborhoods you wander through on your way. For instance, I made a Kenny G to Cannibal Corpse playlist. To get there, the playlist brought me from easy listening, to movie soundtracks and then through video game soundtracks to get to the heavy metal world. Cool stuff. If you want to see a playlist between two artists let me know in the comments and I’ll create and share the playlist with you.
I made a video of Boil the Frog in action. Check it out:
Update: I’ve just pushed the client code out to github: https://github.com/plamere/boilthefrog