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.
|DJ Testosterone's Latest Track: Hearing Rain|
|League of Space Pirates|
|Wooden Bluetooth Speaker Made With 50,000 Year Old Excavated Wood|
|Klenginem: The Official Website|
|NSFW: King Fantastic's "Why? Where? What?" Too Hot For YouTube|
|“Rejuvenation is Finally an Industry.”|
|Everything We've Learnt About the Surveillance State|
|How to Avoid Jury Duty|
|Go the Fuck to Sleep: A Children's Bedtime Book|
|“Put words between buns.”|
|“He portrays these abandoned malls as apocalyptic ruins.”|
|Japanese Robot Serves Ice Cream From Inside a Vending Machine|
|Cure for Gayness? There's an App for That|
|The BROpener: Any Surface Becomes a Bottle Opener|
|Star Wars: The Changes -- Part One|
|“Tesla Model 3: It’s a giant iPhone.”|
|Bizarre Record Covers|