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.
|JAM with Chrome: Play Music Live With Your Friends Online|
|How Speakers Work|
|BBC's David Attenborough Sings What A Wonderful World|
|TomBox: Portable, Unique Recycled Speakers|
|Making Sounds Out of Everyday Things|
|“The idea of the self-empowered Uber driver or Airbnb host is a rarity if not an outright myth.”|
|“It is financially insane to buy anything other than a Tesla.”|
|“The deadlines aren't the problem. It's our failure to heed them.”|
|CaptchaTweet: Write Tweets in Captcha Form|
|The (Very Scary) People of Public Transit|
|How to Avoid Jury Duty|
|U.S.S. Enterprise Owner's Manual|
|Fake Name Generator|
|Naked Preacher Lady [NSFW]|
|“Impossible Aerospace founder and CEO Spencer Gore hopes to make self-flying electric planes.”|
|Recycled Vacuum Lamps|
|“We are undergoing the greatest economic transformation in our history, and we are dealing with it by pretending nothing is happening.”|