I'm the Director of Developer Community at The Echo Nest, a research-focused music intelligence startup that provides music information services to developers and partners through a data mining and machine listening platform. I am especially interested in hybrid music recommenders and using visualizations to aid music discovery.

Music Machinery on Substack

I fondly recall the Google Reader days when lots of folks were reading long form content. With the demise of Google Reader, and the rise of Twitter, TikTok and Instagram, long form content drifted into the background. But it may be coming back, thanks at least in part, to Substack. I’m going to give Substack a try, so you’ll find new content posted at

Leave a comment

My favorite blog post of all time

I’ve been reading blogs seemingly forever. I’ve read lots of great posts .. but there’s one blog post that I still think about all the time even though it is nearly 5 years old. It’s by Sascha Judd and its all boy bands and the diversity crisis in tech. It’s a must read: How The Tech Sector Could Move In One Direction.

The gendered aspect of it kept bugging me.  It seemed like it was okay to be hysterical about some things, but not others.

Someday I may get back to organizing tech events – and when I do, I’ll be thinking about better ways to engage with fan armies.

Leave a comment

Duke Listens! returns (again)

A few months ago, we finally shutdown the final remnants of the old Echo Nest infrastructure. One of casualties of this final shutdown was the archive of my old blog Duke Listens! that I authored while I was a researcher at Sun Labs. However, I did manage to have a backup sitting on an old backblaze disk, so this morning I took a bit of time to re-host it on one of my personal servers. You can find it at:

The blog serves as a reminder of the history of music recommendation and discovery during the iPhone era. Some notable posts:

, ,

Leave a comment

The World’s First MachineLearning-enabled musical keyboard !?!

Today Amazon released AWS DeepComposer which is a keyboard that will let you “create a melody that will transform into a completely original song in seconds”.

AWS DeepComposer keyboard

To me it looks like an Arturia Keystep knock-off.  I’m still puzzling over whether or not there’s any special ML-related features – or is it just a MIDI keyboard that comes with some AWS credits. Anyone with any insights, please let me know.

1 Comment

How Generative Music Works

How Generative Music Works 🔊 2019-12-02 14-35-22

Tero Parvianen has en excellent introduction to Generative Music with lots of live examples. Well worth 20 minutes of your time with lots of food for thought.

How Generative Music Works

Leave a comment

Music Machinery Chapter 2

I’ve spent the last 15 or so years thinking mostly about the machinery that gets music from the bits in an audio recording into the ears of a listener. There are dozens of examples of tools for music discovery, organization and listening in the sidebar at the right on this blog.  But lately I’ve been thinking quite a bit more about the machinery that goes into getting the bits into an audio recording in the first place.  I’m particularly interested in two aspects of this:  (1) music synthesis – the machinery that can create the sounds from scratch and (2) generative music – machinery that can generate the music from scratch.

If you are interested in synthesis and generative music, feel free to follow along in Music Machinery Chapter 2. I’m a newbie at it all so pointers and guidance will be greatly appreciated.



Is this thing on …

Woah, its been a while since I’ve posted to this blog (three and a half years to be exact).  I think it’s time for a bit of a reboot on this blog.  Stay tuned!


Girl Talk In A Box update

2016-04-30 at 7.31 AMI’ve pushed out some updates to GirlTalkInABox – there are now some nifty filters (chorus, phaser, delay and wahwah), and you can interactively adjust the playback rate of the song.  A few other minor changes as well to make live performances a little easier.   Check it out at GirlTalkInABox.



Leave a comment

Smarter Playlists – My Top Tracks

I’ve just added a new Smarter Playlists component called My Top Tracks. This track source will generate a list of the top 50 tracks from your recent listening history.  You can choose from 3 different time ranges:

  • short term – the last month or so
  • medium term – the last half year or so
  • long term – the last several years

The component configuration looks like this:

2016-03-13 at 9.35 AM

Here’s an example program using the new component to surface up tracks that I’ve listened to a lot in the past that haven’t been getting a lot of play time in the last half-year.

2016-03-13 at 9.27 AM

Feel free to try out the new component and send me feedback via the google group.

update – to use the new component, you will need to logout and then log back into SmarterPlaylists to grant it the extra permissions it needs to read your recent play history.




Most popular SmarterPlaylists components

As of this morning, there have been 1,363 SmarterPlaylist programs written.   Currently there are 300 SmarterPlaylist jobs running periodically.  I was wondering what were the most popular components, so I took inventory by looking at all of those 1,363 programs to see which components were used the most often.  Here’s the list:

4046 SpotifyPlaylist
1276 Sample
709 EchoNestGenreRadio
673 Concatenate
563 DeDup
499 PlaylistSave
455 Shuffler
441 TrackFilter
394 EchoNestArtistRadio
325 comment
248 Sorter
225 RelativeDatedSpotifyPlaylist
222 MySavedTracks
218 ArtistTopTracks
217 Alternate
200 PlaylistSaveToNew
194 LongerThan
155 EchoNestArtist
141 First
129 AlbumSource
125 DatedSpotifyPlaylist
117 Mixer
116 ReleaseDateFilter
111 Danceable
108 SeparateArtists
89 MyFollowedArtists
82 AttributeRangeFilter
79 RandomSelector
77 Energy
72 Tempo
69 ArtistDeDup
68 ArtistFilter
56 Explicit
42 MixIn
39 MySavedAlbums
37 IsDayOfWeek
30 TrackSourceByName
25 SimpleArtistFilter
24 AllButTheFirst
20 ArtistSeparation
19 Weighted Shuffler
19 ShorterThan
18 Spoken Word
16 TrackSource
12 RandomStreamSelector
10 Last
5 IsWeekend
4 Live
4 AllButTheLast
4 YesNo
3 Annotator
3 Reverse
1 TextFilter

The big surprises for me were to see how often the Echo Nest Artist and Genre radio are being used, and even after being around for only a week, how often the RelativeDatedSpotifyPlaylist is being used.

Leave a comment