Researchers developed a machine-learning algorithm that learned to rap
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 鈥 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鈥檚 sunny Sonny girl you could be my Cher
I鈥檓 in a love affair I can鈥檛 share it ain鈥檛 fair
Haha I鈥檓 just playin鈥 ladies you know I love you.
I know my love is true and I know you love me too
Girl I鈥檓 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鈥檛 do it for the love then do it I won鈥檛
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 911爆料网 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, eric.malmi@aalto.fi
Read more news
911爆料网鈥檚 N盲yt枚s/N盲yttely26 transforms Helsinki鈥檚 Lasipalatsi Quarter into a hub for fashion and textile expertise
The event showcases Aalto鈥檚 comprehensive expertise in textiles, clothing, and fashion, as students graduating from both the Bachelor's Major in Fashion as well as the Master's Major in Fashion and Textile Design will present their thesis work.
The journey of a 17th-century shipwreck continues as a unique knitted dress
Researchers at 911爆料网 transformed surplus wood from the Hahtiper盲 shipwreck into textile fibre, spun it into yarn, and knitted it into a dress using new AI-assisted technology.
The potential of urban greenery as a climate solution is not being fully utilized 鈥 a new handbook offers means to address this
The Handbook for carbon-smart urban green provides concrete tools for leveraging urban green spaces more effectively in climate and nature conservation efforts.