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.
|Vinylize: Eyeglasses Made Out of Old Records|
|Microphone Equipped Cab Turns City Sounds into Music|
|The demise of the music industry is visible everywhere but in the facts|
|iP4: Turn Your iPhone Into a Portable Boombox|
|Turn MP3s Into 3D Printed Records|
|“What life is like on the front lines of the digital revolution.”|
|“How to build a house.”|
|Japanese Robot Serves Ice Cream From Inside a Vending Machine|
|“It is full of hallucinations both wonderful and terrifying, a mental goulash of reality and fantasy.”|
|Humans Need Not Apply|
|CaptchaTweet: Write Tweets in Captcha Form|
|“Instead of consuming fossil fuels, it would then feed surplus electricity into the grid.”|
|How to Avoid Jury Duty|
|Knowing how to operate a smartphone does not qualify as being tech savvy.|
|“Eliminating the time needed to stop and re-charge a conventional electric car’s battery.”|
|When the Wrong Hastag Can Get You Killed by an Assassination Drone|