Posts Tagged Music

Loudest songs in the world

Lots of ink has been spilled about the Loudness war and how modern recordings keep getting louder as a cheap method of grabbing a listener’s attention.   We know that, in general, music is getting louder. But what are the loudest songs? We can use The Echo Nest API to answer this question.  Since the Echo Nest has analyzed millions and millions of songs, we can make a simple API query that will return the set of loudest songs known to man.  (For the hardcore geeks, here’s the API query that I used).   Note that I’ve restricted the results to those in the 7Digital-US catalog in order to guarantee that I’ll have a 30 second preview for each song.

So without further adieu, here are the loudest songs

Topping and Core by Grimalkin555

The song Topping and Core by Grmalking555 has a whopping loudness of  4.428 dB.

Modifications by Micron

The song Modifications  by Micron has a loudness of  4.318 dB.

Hey You Fuxxx! by Kylie Minoise

The song Hey You Fuxxx! by Kylie Minoise with a loudness of 4.231 dB

Here’s a little taste of Kylie Minoise live (you may want to turn down your volume)

War Memorial Exit by Noma

The song War Memorial Exit by Noma with a loudness of 4.166 dB

Hello Dirty 10 by Massimo

The song Hello Dirty 10 by Massimo with a loudness of 4.121 dB.

These songs are pretty niche. So I thought it might be interesting to look the loudest songs culled from the most popular songs.  Here’s the query to do that.  The loudest popular song is:

Welcome to the Jungle by Guns 'N Roses

The loudest popular song is Welcome to the Jungle by Guns ‘N Roses with a loudness of -1.931 dB.

You may be wondering how a loudness value can be greater than 0dB.  Loudness is a complex measurement that is both a function of time and frequency.  Unlike traditional loudness measures, The Echo Nest analysis models loudness via a human model of listening,  instead of  directly mapping loudness  from the recorded signal. For instance, with a traditional dB model a simple sinusoidal function would be measured as having the same exact “amplitude” (in dB) whether at 3KHz or 12KHz. But with The Echo Nest model, the loudness is lower at 12KHz than it is at 3KHz because you actually perceive those signals differently.

Thanks to the always awesome 7Digital for providing album art and 30 second previews in this post.

, ,


25 SXSW Music Panels worth voting for

Yesterday, SXSW opened up the 2012 Panel Picker allowing you to vote up (or down) your favorite panels.  The SXSW organizers will use the voting info to help whittle the nearly 3,600 proposals down to  500.  I took a tour through the list of music related panel proposals and selected a few that I think are worth voting for. Talks in green are on my “can’t miss this talk” list.  Note that I work with or have collaborated with many of the speakers on my list, so my list can not be construed as objective in any way.

There are many recurring themes. is everywhere. Everyone wants to talk about the role of the curator in this new world of algorithmic music recommendations. And Spotify is not to be found anywhere!

I’ve broken my list down into a few categories:

Social Music – there must be a twenty panels related to social music. (Eleven(!) have something to do with My favorites are:

    • Social Music Strategies: Viral & the Power of Free – with folks from MOG, Turntable, Sirius XM, Facebook and Fred Wilson.  I’m not a big fan of big panels (by the time you get done with the introductions, it is time for Q&A), but this panel seems stacked with people with an interesting perspective on the social music scene. I’m particularly interested in hearing the different perspectives from Turntable vs. Sirius XM.
    • Can Social Music Save the Music Industry? – Rdio, Turntable, Gartner, Rootmusic, Songkick – Another good lineup of speakers ( is everywhere at SXSW this year) exploring social music.  Curiously, there’s no Spotify here (or as far as I can tell on any talks at SXSW).
    • the Future of Music is Social – – This is the story.
    • Reinventing Tribal Music in the land of Earbuds – AT&T –  this talk explores how music consumption changes with  new social services and the technical/sociological issues that arise when people are once again free to choose and listen to music together.

Man vs. Machine – what is the role of the human curator in this age of algorithmic recommendation and music.  Curiously, there are at least 5 panel proposals on this topic.

Music Discovery – A half dozen panels on music recommendation and discovery.  Favs include:

Mobile Music – Is that a million songs in your pocket or are you just glad to see me?

Big Data – exploring big data sets to learn about music

Echo Nesty panels – proposals from folks from the nest. Of course, I recommend all of these fine talks.

    • Active Listening – Tristan Jehan – Tristan takes a look at how the music experience is changing now that the listener can take much more active control of the listening experience.  There’s no one who understands music analysis and understanding better than Tristan.
    • Data Mining Music Paul Lamere – This is my awesome talk about extracting info from big data sets like the Million Song Dataset. If you are a regular reader of this blog, you’ll know that I’ll be looking at things like click track detectors, passion indexes, loudness wars and son on.
    • What’s a music fan worth? – Jim Lucchese – Echo Nest CEO takes a look at the economics of music, from iOS apps to musicians.  Jim knows this stuff better than anyone.
    • Music Apps Gone Wild – Eliot Van Buskirk – Eliot takes a tour of the most advanced, wackiest music apps that exist — or are on their way to existing.
    • Curation in the age of mechanical recommendations – Matt Ogle – Matt is a phenomenal speaker and thinker in the music space.  His take on the role of the curator in this world of algorithms is at the top of my SXSW panel list.
    • Editor vs. Algorithm in the Music Discovery Space – SPIN, Hype Machine, Echo Nest (Jim Lucchese), 7Digital
    • Defining Music Discovery through Listening – Echo Nest (Tristan Jehan), Hunted Media – This session will examine “true” music discovery through listening and how technology is the facilitator.

Miscellaneous topics

Well, there you have it – my 25 top music talks for SXSW 2012. Don’t forget to vote!

, ,

Leave a comment

Data Mining Music – a SXSW 2012 Panel Proposal

I’ve submitted a proposal for a SXSW 2012 panel called Data Mining Music.  The PanelPicker page for the talk is here:  Data Mining Music.  If you feel so inclined feel free to comment and/or vote for the talk. I promise to fill the talk  with all sorts of fun info that you can extract from datasets like the Million Song Dataset.

Here’s the abstract:

Data mining is the process of extracting patterns and knowledge from large data sets. It has already helped revolutionized fields as diverse as advertising and medicine. In this talk we dive into mega-scale music data such as the Million Song Dataset (a recently released, freely-available collection of detailed audio features and metadata for a million contemporary popular music tracks) to help us get a better understanding of the music and the artists that perform the music.

We explore how we can use music data mining for tasks such as automatic genre detection, song similarity for music recommendation, and data visualization for music exploration and discovery. We use these techniques to try to answers questions about music such as: Which drummers use click tracks to help set the tempo? or Is music really faster and louder than it used to be? Finally, we look at techniques and challenges in processing these extremely large datasets.

Questions answered:

  1. What large music datasets are available for data mining?
  2. What insights about music can we gain from mining acoustic music data?
  3. What can we learn from mining music listener behavior data?
  4. Who is a better drummer: Buddy Rich or Neil Peart?
  5. What are some of the challenges in processing these extremely large datasets?

Flickr photo CC by tristanf

, ,

Leave a comment

Where did my Google Music go?

I just fired up my Google Music account this afternoon and this is what I found:

 All 7,861 songs are gone.  I hope they come back.  Apparently, I’m not the only one this is happening to.

Update – all my music has returned sometime overnight.



The Wub Machine

Peter Sobot (@psobot ) has used The Echo Nest Remix to automatically add dubstep to any song.

The Crash Bandicoot Dubset remix is pretty wild.  Peter says that The Wub Machine is still work in progress. Check out how it works and add your ideas to the mix on Peter’s blog.

, , ,

Leave a comment

What’s your favorite music visualization for discovery?

In a couple of weeks I’m giving a talk at SXSW called Finding Music with pictures : Data visualization for discovery. In this panel I’ll talk about how visualizations can be used to help people explore the music space and discover new, interesting music that they will like.  I intend to include lots of examples both from the commercial world as well as from the research world.

Ishkur's guide to electronic music - One of my favorite visualizations for discovery

I’ll be drawing material from many sources including the Tutorial that Justin and I gave at ISMIR in Japan in October 2009:  Using visualizations for music discovery.  Of course lots of things have happened in the year and a half since we put together that tutorial such as  iPads, HTML5, plus tons more data availability.  If you happen to have a favorite visualization for music discovery, post a link in the comments or send me an email: paul [at]


, , ,


What’s the TTKP?

Whenever Jennie and I are in the car together,  we will listen to the local Top-40 radio station (KISS 108).  One top-40 artist that i can recognize reliably is Katy Perry.  It seems like we can’t drive very far before we are listening to Teenage Dreams, Firework or California Gurls.   That got me wondering what the average Time To Katy Perry  (TTKP) was on the station and how it compared to other radio stations. So I fired up my Python interpreter, wrote some code to pull the data from the fabulous YES api and answer this very important question.  With the YES API I can get the timestamped song plays for a station for the last 7 days.  I gathered this data from WXKS (Kiss 108), did some calculations to come up with this data:

  • Total songs played per week:  1,336
  • Total unique songs: 184
  • Total unique artists: 107
  • Average songs per hour: 7
  • Number of Katy Perry plays: 76
  • Median Time between Katy Perry songs:  1hour 18 minutes

That means the average Time to Katy Perry is about 39 minutes.

Katy Perry is only the fourth most played artist on KISS 108.  Here are the stats for the top 10:

Artist Plays Median time
between plays
Average time
to next play
Taio Cruz 84 1:07 0:34
Rihanna 80 1:27 0:44
Usher 79 1:20 0:40
Katy Perry 76 1:18 0:39
Bruno Mars 73 1:30 0:45
Nelly 56 1:44 0:52
Mike Posner 56 1:57 0:59
Pink 47 2:20 1:10
Lady Gaga 47 1:59 1:00
Taylor Swift 41 2:17 1:09

I took a look at some of the other top-40 stations around the country to see which has the lowest TTKP:

Station Songs Per Hour TTKP
KIIS – LA’s #1 hit music station 8 39 mins
WHTZ- New York’s #1 hit music station 9 48 mins
WXKS- Boston’s #1 hit music station 7 39 mins
WSTR- Atlanta – Always #1 for Today’s Hit Music 8 38 mins
KAMP- 97.1 Amp Radio – Los Angeles 11 38 mins
KCHZ- 95.7 – The Beat of Kansas City 11 32 mins
WFLZ- 93.3 – Tampa Bay’s Hit Music channe 9 39 mins
KREV- 92.7 – The Revolution – San Francisco 11 36 mins

So, no matter where you are, if you have a radio, you can tune into the local top-40 radio station, and you’ll need to wait, on average, only about 40 minutes until a Katy Perry song comes on. Good to know.

, , , ,


testing one of the new APIs

nest% least_energy the beatles
0.08 Julia
0.09 Yesterday
0.11  Golden Slumbers
0.11 Blackbird  / Yesterday

nest% least_danceable the beatles
0.02 Revolution 9
0.07 Within You Without You _ Tomorrow Never Knows
0.07  Because

nest% most_energy led zeppelin
0.98 Moby Dick — Bonzo’s Montreux
0.98 Bonzo’s Montreux
0.95 Walter’s Walk
0.95 D’yer Mak’er

nest% most_danceable led zeppelin
0.73 Black Country Woman
0.64 Boogie With Stu
0.63 All My Love
0.63 The Rover

, , , ,


Cool music panels at SXSW 2011

I was going to write a post describing all of the cool looking music-oriented panels that have been proposed for SXSW 2011, but debcha at zed equals zee beat me to it.  Be sure to read Deb’s SXSWi 2011 panel proposals in music and tech post.  Some of the panels I’m looking to the most are:

Digital Music Smackdown: The Best Digital Music ServiceIn what is expected to be a heated and fiercely competitive discussion, C and VP-level executives from four digital music companies (MOG, Spotify, Pandora and Rhapsody) battle it out over the title of “Best Digital Music Service.  This could be fun if it is really a smackdown, but I suspect that the execs will be very polite and complimentary of each other’s services leading to a boring panel.  I hope I’m wrong.  Also, where’s – they should be on the panel too.

We Built this App on RocknRoll: Style MattersFor an inherently auditory medium, music is ingrained with style. From 12″ artwork and niche mp3 blogs to the latest design on your sweatshirt or skate deck, music has always been analogous with visual culture. So what happens when you overlay this complex fabric of cultural values and personal identities on what is already a thorny process: building and launching a music app. – Hannah of and Anthony of Hype Machine talk about the design of music apps. These two know their stuff. Should be really interesting.

Music & Metadata: Do Songs Remain the Same? Metadata may be an afterthought when it comes to most people’s digital music collections, but when it comes to finding, buying, selling, rating, sharing, or describing music, little matters more. Metadata defines how we interact and talk about music—from discreet bits like titles, styles, artists, genres to its broader context and history. Metadata builds communities and industries, from the local fan base to the online social network. Its value is immense. But who owns it? This panel is on my Must See list.

Expressing yourself musically with Mobile Technology This is a panel with Ge Wang, founder/CTO of Smule talking about creating music on mobile devices.  Ge is an awesome speaker and gives great demo. Don’t miss this one.

Music APIs – A Choreographed Dance with Devices?This panel discussion focuses on real-world examples beyond the fundamentals or technical aspects of an API. Attend this panel and review success stories from the pros that demonstrate how an API brings content, software, and hardware together. Looks like a good Music APIs 101 for biz types.

I would be remiss if I didn’t pimp my own panels.  Be sure to consider (and maybe even comment on / vote for ) these panels:

Love, Music & APIs. Consider this to be the Music Hack Day panel. Dave Haynes (SoundCloud) and  I will talk about the impact that Music APIs are having on the world of music and how programmers will soon be the new music gamekeeper.

Finding Music With Pictures: Data Visualization for Discovery:   In this panel I’ll  look at how visualizations can be used to help people explore the music space and discover new, interesting music that they will like. We will look at a wide range of visualizations, from hand drawn artist maps, to highly interactive, immersive 3D environments.

The folks at SXSW are looking for input on these panels to help decide what makes it onto the schedule, so if any of these strike your fancy, head on over to the panel descriptions and add your comments.


Leave a comment

Echo Nest Remix at the Boston Python Meetup Group

Next week I’ll be giving a talk about remixing music with Echo Nest remix at the Boston Python Meetup Group.  If you are in the Boston / Cambridge area next week, be sure to come on by and say ‘hi’.  Info and RSVP for the talk are here:  The Boston Python Meetup Group on

Here’s the abstract for the talk:

Paul Lamere will tell us about Echo Nest remix. Remix is an open source Python library for remixing music. With remix you can use Python to rearrange a track, combine it with others, beat/pitch shift it etc. – essentially it lets you treat a song like silly putty.

The Swinger is an interesting example of what it can do that made the rounds of the blogosphere: it morphs songs to give them a swing rhythm.

For more details about the type of music remixing you can do with remix, feel free to read: http://musicmachinery…

, ,

Leave a comment