Tag Archives: music

06May / 2020

Remix and make music with audio from the Library of Congress

Brian Foo is the current Innovator-in-Residence at the Library of Congress. His latest project is Citizen DJ, which lets you explore and remix audio from the Library:

It invites the public to make hip hop music using the Library’s public audio and moving image collections. By embedding these materials in hip hop music, listeners can discover items in the Library’s vast collections that they likely would never have known existed. For technical documentation and code, please see the repo.

Give it a go. Even if you’re not into making music, you can still explore the sounds, listen to them in their full context, and end up reading about some song written in the early 1900s.

I’ll take all the rabbit holes I can get.

Tags: , ,

Posted by in apps, Brian Foo, Library of Congress, Music

Tags: , ,

Permalink

01May / 2020

Looking for generational gaps in music

Inspired by the genre of YouTube videos where younger people listen to older music, The Pudding is running a project to find the generational music gaps. Enter your age, songs play, and you say if you know the song or not.

The aggregate results are shown as more people listen. For example, the above shows the percentage of people in a given age group who did not recognize the listed songs.

I’m looking forward to what they do with the finished dataset.

Tags: , ,

Posted by in generations, Music, Pudding, statistics

Tags: , ,

Permalink

30Apr / 2020

Neural network generates convincing songs by famous singers

Jukebox from OpenAI is a generative model that makes music in the same styles as many artists you’ll probably recognize:

To train this model, we crawled the web to curate a new dataset of 1.2 million songs (600,000 of which are in English), paired with the corresponding lyrics and metadata from LyricWiki. The metadata includes artist, album genre, and year of the songs, along with common moods or playlist keywords associated with each song. We train on 32-bit, 44.1 kHz raw audio, and perform data augmentation by randomly downmixing the right and left channels to produce mono audio.

A lot of the time, generative music sounds artificial and mechanical, but these results are pretty convincing. I mean you can still tell it’s not from the artist, but many of the examples are listenable.

OpenAI also published the code.

Tags: , , ,

Posted by in Jukebox, Music, neural network, OpenAI, statistics

Tags: , , ,

Permalink

23Apr / 2020

Testing the infinite monkey theorem

If you have a room of monkeys hitting keys on typewriters for an infinite amount of time, do you eventually end up with a Shakespeare play? For The Pudding, Russell Goldenberg and Amber Thomas put the infinite monkey theorem to the test directing the computer to randomly generate musical note patterns to match classic songs.

All said and done, the point here isn’t the real numbers, but the faith that given enough time, randomness will prevail. Will our experiment eventually play even the simple Nokia ringtone in our lifetime? Almost certainly not. Given enough time would it? Almost surely.

The experiment has been running for 10 days so far, currently working on “Another One Bites the Dust” by Queen.

Tags: , ,

Posted by in infinite monkey, Music, Pudding, statistics

Tags: , ,

Permalink

23Jan / 2020

Geography of FM radio

So get this. There are these things called radio stations that broadcast music using frequency modulation. They call it “FM radio.” You don’t download or stream the music, and you don’t get to choose what songs you want to hear right away, but sometimes you can call locally and request a song you like. It’s also free to listen to if you have this thing called a “radio.” In exchange, you have to listen to “commercials” sometimes where someone tries to sell you stuff. Seems like a fair exchange.

Anyways, Erin Davis mapped these radio stations and their coverage, based on FCC data. She joined the data with radio-locator.com data, which provides music genre. This allowed for the splits above.

Technology is amazing.

Tags: ,

Posted by in maps, Music, radio

Tags: ,

Permalink

16Aug / 2019

Measuring pop music’s falsetto usage

Vox and Matt Daniels delved into falsetto in pop music over the years. Is falsetto a big trend now compared to the rest of the history? The process of finding the answer, noisy data and all, was just as interesting as the answer itself.

Tags: , , ,

Posted by in falsetto, Infographics, Matt Daniels, Music, Vox

Tags: , , ,

Permalink

19Nov / 2018

Neural networks to generate music

Kyle McDonald describes some of the history and current research on using algorithms to generate music. On how David Cope incorporated Markov chains to aid in his work:

In 1981 David Cope began working with algorithmic composition to solve his writers block. He combined Markov chains and other techniques (musical grammars and combinatorics) into a semi-automatic system he calls Experiments in Musical Intelligence, or Emmy. David cites Iannis Xenakis and Lejaren Hiller (Illiac Suite 1955, Experimental Music 1959) as early inspirations, and he describes Emmy in papers, patents, and even source code on GitHub. Emmy is most famous for learning from and imitating other composers.

I expected samples to sound robotic and unnatural, and some are, but some are quite pleasant to listen to.

Tags: ,

Posted by in Music, neural network, statistics

Tags: ,

Permalink

10Aug / 2018

Charting the similarity of summer songs

Popular summer songs have had a bubbly, generic feel to them the past several years, but it wasn’t always like that. Styles used to be more diverse, and things might be headed back in that direction. Sahil Chinoy and Jessia Ma charted song fingerprints over the years for a musical comparison.

Turn up your speakers or put on your headphones for the full experience. The song and music video snippets provide a much better idea of what the charts represent.

Tags: , ,

Posted by in Infographics, Music, New York Times, summer

Tags: , ,

Permalink

31Jul / 2018

Finding the Beatle who wrote each song using statistical models

There’s been some disagreement about who wrote “In My Life” by The Beatles, so researchers did what any normal person does and tried to model the songs of Paul McCartney and John Lennon:

Mark Glickman, senior lecturer in statistics at Harvard University, and Jason Brown, Professor of Mathematics at Dalhousie University, created a computer model which broke down Lennon and McCartney songs into 149 different components to determine the musical fingerprints of each songwriter.

McCartney says he wrote the music for the song, but Glickman and Brown give that claim a less than 1 in 50 chance.

Tags: ,

Posted by in Beatles, Music, statistics

Tags: ,

Permalink

25May / 2018

Increasing similarity of Billboard songs

Popular songs on the Billboard charts always tended to sound similar, but these days they’re sounding even more similar. Andrew Thompson and Matt Daniels for The Pudding make the case:

From 2010-2014, the top ten producers (by number of hits) wrote about 40% of songs that achieved #1 – #5 ranking on the Billboard Hot 100. In the late-80s, the top ten producers were credited with half as many hits, about 19%.

In other words, more songs have been produced by fewer and fewer topline songwriters, who oversee the combinations of all the separately created sounds. Take a less personal production process and execute that process by a shrinking number of people and everything starts to sound more or less the same.

Tags: , , ,

Posted by in Billboard, Music, Pudding, songs, statistics

Tags: , , ,

Permalink