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.
|Audiowood's Turntables Mounted on Solid Tree Rounds|
|Experiments Around the House by Lullatone|
|Sewing Machine Orchestra|
|Everyday Normal Guy|
|Pianocade: Synthesizer Designed to Sound, Look, and Feel Like Vintage Arcade Games|
|“I can’t wait for the day robots rule.”|
|“Changes to the platform announced by Zuckerberg, will likely make the problem worse.”|
|“AI codes its own ‘AI Child’.”|
|Pat the Zombie: A Cruel Adult Spoof of 'Pat the Bunny'|
|“The first-ever driverless mass transit test program.”|
|How to Avoid Jury Duty|
|How to Escape Planet Earth|
|“The e-Palette, a vehicle that may one day not only deliver, but cook Pizza Hut offerings en route.”|
|“Scientific evidence that digital distraction is damaging our minds.”|
|“Some of us will do anything to be liked.”|
|“Imagine if you were allowed to eat as many M&M’s as you wanted.”|
|“The idea is to extract value from customers in the name of absurd growth.”|