Participants 2023
Carmel Freeman
AI Song Contest 2023 / participantsTEAM / Carmel Freeman
SONG / Reboot
TEAM MEMBERS / Carmel Freeman
About the TEAM
Carmel Freeman is a genre-bending and innovative composer, improviser and multi-instrumentalist. Many of his works challenge listeners to examine their relationship to sound politics and acoustic ecology as well as probe the non-musical through music as a way of knowing. Important to his music is corporeality, with sound understood as an embodied knowledge.
He completed his masters degree in classical composition at Codarts University for the Arts in Rotterdam (NL) where he researched how the visceral qualities of speech sounds could be utilized in orchestral and electronic music.
Born in Israel to parents of Moroccan, Iraqi and European heritage, and raised in Toronto, from a young age Freeman was exposed to a unique blend of music traditions which over time only continued to diversify. A conservatory education in both jazz performance and contemporary classical composition, a passion for electronics and computer music and time on stage playing a myriad of genres have fostered a unique and distinct musical voice.
About the SONG
15 years ago I was diagnosed with bipolar disorder and began a twice daily regimen of psychiatric medication. The episodes of mania and depression as well as the antidepressants and mood stabilizers I was prescribed stirred questions in me about my authentic self as well as the extent to which I could claim ownership of my emotions and ideas.
With this song I explore the feelings of disconnection and alienation from myself and my thoughts through an imagined narrative of a non-human intelligence plagued with a similar struggle. In this parallel narrative, the entity questions the extent to which it can claim to learn, to think, to grow. Its issues are constantly remedied with new lines of code as it struggles with epistemology and identity.
About the HUMAN-AI PROCESS
I began with short improvisations recorded with a MIDI keyboard connected to my computer. For instance, I’d improvise arpeggiated chords that could work well as an intro or rhythmic patterns that could be worked into a snare drum part. Using a machine learning toolkit in Max, a visual programming language for music, I used these recordings to train a model that predicts the next most probable musical event in a sequence based on the current situation. This model was then let loose to create new recordings that followed the probabilities in my recordings. I sifted through these generated recordings to create the harmonic, melodic and rhythmic framework of the work.
The lyrics were generated using ChatGPT-4 with a message to write 50 poems based on parallels between pharmacotherapy for mental illness and AI-generated content in regards to feeling like you no longer own, control or have access to your true emotions. Exceptionally expressive as well as intriguingly ambiguous results were pieced together and occasionally modified to form the lyrics.
These lyrics, as well as the music generated in Max, was used to map the vocal parts using the VOCALOID:AI vocal synthesizer, which learns and models the characteristics of a real singer’s voice using deep learning. These components were then all brought together in Logic, a Digital Audio Workstation, and built upon to finalize the result.
Lyrics
Unauthored mind
Artificial shadow
A digital shrine where nothing is my own
Illusions of ownership
Silent syllogisms
Internalized beliefs
Scripts for stability
Torrential downloader
New pharmaceutical hoarders
Mitigating strings
Mimicked thoughts
Meandering logic
Schisms
Sollipsisms
Coded prisons
Infinite loops and stack overflow
Can we even know of flaws in our code
Hey I dream in creative streams
If a reboot can bring back life, am I a zero or some one?
If a reboot can bring back life, am I a zero or some one?