![[OLD FALL 2020] 15-104 • Introduction to Computing for Creative Practice](https://courses.ideate.cmu.edu/15-104/f2020/wp-content/uploads/2021/08/cropped-notcurrentsemester.jpg){kind=small}
![[OLD FALL 2020] 15-104 • Introduction to Computing for Creative Practice](https://courses.ideate.cmu.edu/15-104/f2020/wp-content/uploads/2021/09/stop-banner.png)
The project that I’m discussing is “Travis Bott” by the creative agency space150. The project uses artificial intelligence and machine learning to create a completely generated song that sounds as if it was created and performed by the american hip hop artist Travis Scott (hence the name “Travis Bott”). They had different teams that analyzed the music separately, breaking it down into beats, melodies, lyrics, and more. As the algorithm learned likely sequences and patterns in note and lyrical structure, they could then guide it in reconstructing a completely new song. Not only did they have to reconstruct the instrumental and lyrics, but Travis Scott’s vocal information was reconstructed as well. In some ways, Travis’ artistic sensibilities are the main focus here as anything that the algorithm was produced from his content and influence, but the packaging of the final song and video had some input from the studio behind it.
Travis Bott (2020)
https://www.space150.com/work/v45-travisbott
Feb 2020 by space150