Technology Review showcases DeepBeat, a computer algorithm that is able to outperform human rappers by 21% in "terms of length and frequency of the rhymes".
The highly structured nature of rap makes it particularly amenable to computer analysis. And that raises an interesting question: if computers can analyze rap lyrics, can they also generate them?
Today, we get an affirmative answer thanks to the work of Eric Malmi at the University of Aalto in Finland and few pals. These guys have trained a machine-learning algorithm to recognize the salient features of a few lines of rap and then choose another line that rhymes in the same way on the same topic. The result is an algorithm that produces rap lyrics that rival human-generated ones for their complexity of rhyme.
|music For Programming();|
|Califone.Stitches: Music Video Made With Random Tumblr Images|
|Start Your Weekend Right With DJ Testosterone|
|Vinylize: Eyeglasses Made Out of Old Records|
|She Drinks More Bourbon Than You Wine You Wine|
|Fake Name Generator|
|“A machine meant to hurl rockets into space.”|
|“The only thing worse than assuming that carbon removal will save the day is assuming it will save the day.”|
|Japanese Robot Serves Ice Cream From Inside a Vending Machine|
|Chinese warehouse organises, packs, and fulfills 200,000 orders a day with four people|
|How to Avoid Jury Duty|
|What Computers See When They Watch a Movie|
|CaptchaTweet: Write Tweets in Captcha Form|
|The (Very Scary) People of Public Transit|
|“Are the puppets coming for our jobs?”|
|Recycled Vacuum Lamps|
|David Reeves' Paper Cutouts Inspired by Classic Cult Movies|