Neural Synthesis Leads to Computer Generated Black Metal

May 03, 2019

I’m going to shift the way this blog is organized. A curriculum-style blog that narrows from recognizing to harmonics isn’t reflective of my internship or musical career. Instead, I’ve decided that the final presentation will take that form. For the blog, I’ll spend more time talking about my experiences and internship, tying that into the research I’m doing on the side. That said, something really cool happened last week that I wanted to share.

You’re listening to live music by Dadabots. This audio stream, generated in real time, is a 24/7 Black Metal performance performed via a process called Neural Synthesis, utilizing the timbres and techniques of a real metal band, and processing that data to create new music indefinitely.
Their process did not perfectly mirror the Black Metal genre, and unintentionally introduced new elements into the mix that the creators ended up enjoying. “While we set out to achieve a realistic recreation of the original data, we were delighted by the aesthetic merit of its imperfections. Solo vocalists become a lush choir of ghostly voices, rock bands become crunchy cubist-jazz, and cross-breeds of multiple recordings become a surrealist chimera of sound. Pioneering artists can exploit this, just as they exploit vintage sound production (tube warmth, tape-hiss, vinyl distortion, etc),” (Zukowski 2). Thus, this neverending performance not only shows how music can be interpreted or simulated using math, but also that math and computers can introduce new types of music when used in creative ways. This theme will recur as I continue my senior project.

Leave a Reply

Your email address will not be published. Required fields are marked *