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.
|He-Man Breakbit Music|
|What Happens When a GoPro Camera and a Trombone Meet|
|17-20-23: @AlexDainis' Six Years in the Making Lip-Sync Video|
|Eulogy to the iPod|
|Searching for Rikki Rockett|
|“Self-driving trucks will begin hauling mail between USPS facilities.”|
|“For the first time in the history of life, we can affect the future of our evolution.”|
|The (Very Scary) People of Public Transit|
|CaptchaTweet: Write Tweets in Captcha Form|
|U.S.S. Enterprise Owner's Manual|
|Recycled Vacuum Lamps|
|“A deep fake sex video emerges in a Google search of your name.”|
|“A driverless electric truck began daily freight deliveries on a public road.”|
|“The company is losing billions, has essentially no underlying value, and its business could be hammered overnight.”|
|Naked Preacher Lady [NSFW]|
|“A new residential building under construction will feature a flying car skyport on the roof.”|
|“We are undergoing the greatest economic transformation in our history, and we are dealing with it by pretending nothing is happening.”|