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 Remix: Too Hot To|
|'Get By' by Delta Heavy: Using Games as Frequency Spectrums|
|New iPod nano uses human skin to transmit audio|
|“The Reality of Building Fantasy.”|
|“That is actually not the way the world has worked for most of human history.”|
|U.S.S. Enterprise Owner's Manual|
|“How did different tooth replacement strategies evolve?”|
|How to Avoid Jury Duty|
|“Systemd is, to put it mildly, controversial.”|
|CaptchaTweet: Write Tweets in Captcha Form|
|iPhone 6, the First Smartphone to Disrupt NSA's Spying|
|The (Very Scary) People of Public Transit|
|“The Amazon Dash button for horny men and women who don’t feel comfortable telling their partner they’d like to have sex.”|
|“If you’re dating, you’re going to be let down. You’re not going to be everyone’s cup of tea.”|
|Testing Whether the Earth is Round or Flat|