App -> https://hafiyyandi.github.io/latent_space_sequencer/index.html Last week after class I tried training a performanceRNN model with my Yoko Shimomura with more steps (>30,000), but it didn’t give me a good generation without perpetually-sustained notes. Because of that failure and the past performances, for this final performance I want to create something that moves beyond generating musical phrases similar to my dataset. I decided to use MusicVAE.js to create music fro

In the past performances, I encoded and trained each track in my MIDI files (melody & harmony) separately. Then I play the generated tracks on the same time. But I think that was not the proper way of generating two-track music, because the melody and harmony should correlate. So for this assignment, I tried using Performance_RNN workflow to encode the dataset and train the model. Dataset I used the same dataset I trained my 2nd performance with: 20 MIDI files of Yoko Shimomu

https://docs.google.com/presentation/d/1Voc7hMwNXKl3Zid9rSsn39cvJW-1YWekGH3e8mP-D2o/edit?usp=sharing #GenerativeMusic

In the first performance, I frankenstein-ed 3 of my favorite songs with Markov chain and generate a midi file as an output. For this performance, I essentially planned to do the same, but with added objectives of: (1) having a more meaningful data corpus, and (2) designing a performance with the generated music that makes sense. This project has been more of a proof-of-concept of a "duet" pipeline. (1) Meaningful data corpus Playing games was a huge part of my childhood, and

Bias in Youtube Recommendation / Flagging Algorithm Social platforms like Facebook, Instagram, Youtube, and Twitter host and distribute enormous amount of content everyday, every second. The extent of influence that these platforms have on our lives and on our society is extremely pervasive: for some people, these platforms are the internet, the only place the get content from. One platform hosting the longest-type content is Youtube. Long(ish) form of video is, I think, uniq

Concept I started with the question: Could I take the songs I absolutely adore, boil them down to its essence, and make a new song out of them? So in this exercise / experiment, I intended to Markov chain 3 of my favorite songs into a single Franken-song. Here are the ingredients: (1) Dearly Beloved, from Kingdom Hearts OST by Yoko Shimomura (2) Passionfruit, from More Life by Drake (3) Gymnopedie No.1 by Erik Satie And this was my workflow: Find MIDI version of these songs P

(1) Terry Riley's In C I listened to a few of "In C" performances. I personally like the versions with non-western instruments / elements. One of these is a performance at Tate Modern conducted by André de Ridder. Coming from Indonesia, I was curious if there was a rendition of "In C" in a pentatonic scale. I found one video, but I am not sure if this is a proper performance of "In C". It does not seem like the individual players make their own phrase choices. Regardless, I r