News

Researchers developed a machine-learning algorithm that learned to rap

DeepBeat, an algorithm for rap lyrics generation, outperforms top human rappers by 21 % in terms of length and frequency of the rhymes in the lyrics.

The rapping algorithm was quantitatively evaluated with two measures. First, the prediction performance was evaluated by measuring how well the algorithm predicts the next line of an existing rap song. This it can do surprisingly well.

- An 82% accuracy was achieved for separating the true next line from a randomly chosen line, says researcher Eric Malmi.

Second, a rhyme density measure was  introduced  and  showed that DeepBeat, an algorithm for rap lyrics generation, outperforms the top human rappers by 21 % in terms of length and frequency of the rhymes in the produced lyrics.

The validity of the rhyme density measure was assessed by conducting a human experiment which showed that the measure correlates with a rapper's own notion of technically skilled lyrics.

Here is one DeepBeat generated on the topic of love:

For a chance at romance I would love to enhance
But everything I love has turned to a tedious task
One day we gonna have to leave our love in the past
I love my fans but no one ever puts a grasp
I love you momma I love my momma – I love you momma
And I would love to have a thing like you on my team you take care
I love it when it’s sunny Sonny girl you could be my Cher
I’m in a love affair I can’t share it ain’t fair
Haha I’m just playin’ ladies you know I love you.
I know my love is true and I know you love me too
Girl I’m down for whatever cause my love is true
This one goes to my man old dirty one love we be swigging brew
My brother I love you Be encouraged man And just know
When you done let me know cause my love make you be like WHOA
If I can’t do it for the love then do it I won’t
All I know is I love you too much to walk away though

Future work could focus on refining storylines, and ultimately integrating a speech synthesizer that would give DeepBeat also a voice.

Researchers Eric Malmi and Pyry Takala, professors Tapani Raiko and Aristides Gionis from the Department of Computer Science at the Aalto University and professor Hannu Toivonen from the University of Helsinki and HIIT developed a machine-learning algorithm that learned to rap. To train the machine-learning algorithm, the researchers began with a database of over 10,000 songs from more than 100 rap artists.

More information:

Eric Malmi, [email protected]

DopeLearning: A Computational Approach to Rap Lyrics Generation

  • Published:
  • Updated:
Share
URL copied!

Related news

Suomessa kehitettiin tekoäly, joka ymmärtää paremmin ihmisen tavoitteita
Research & Art Published:

Designing AI that understands humans’ goals better

To make a better smart assistant, we need an AI that understands its user and does not constantly need detailed instructions
Oniipa
Research & Art Published:

Researchers are importing electricity and internet connections to a Namibian village – required technology can be transported in a pickup

The initiative to be piloted on Independence Day seeks to aid the everyday lives of people in small communities while creating a framework for businesses.
Polymer film that bends when light is shone on it
Research & Art Published:

Liquid crystal polymer learns to move and grab objects

Researchers trained material the same way as Pavlov trained dogs.
Veronika Honkasalon puku
Cooperation, Research & Art Published:

Member of Parliament Veronika Honkasalo’s independence day dress reflects feminism and ecological values

Aalto University FaCT MA student Heidi Karjalainen has designed MP Veronika Honkasalo’s (Left Alliance) dress for the President’s Independence Day Reception 2019.