Participants 2022
Machine Forgetting
AI Song Contest 2022 / participantsTEAM / Machine Forgetting
SONG / Amour Stochastique
TEAM MEMBERS / Ninon Lizé Masclef, Tomasz Sroczyński
About the TEAM
Tomasz Sroczyński is a Polish violinist and techno music producer. Last year his second symphony for violin and sampler was released by the French label Ici d'ailleurs.
Ninon Lizé Masclef is a French multimedia artist and ML engineer. Previously Research Assistant at Deezer, she is currently Artist in Residence at Dassault Systèmes.
The couple works between Paris and the Polish mountains Babia Góra. While Tomasz had no prior experience working with AI before meeting Ninon, the majority of her artistic projects involve generative models for visual arts and real-time AI performance.
The first experience of the duo using creative AI together was during an audiovisual poetry performance during Różewicz Open Festival 2021, where Ninon generated 3D graphics reacting in real time to the acoustic features of the violin of Tomasz and poems.
About the SONG
In Amour Stochastique, we wanted to combine our contemporary culture with ancient traditions, mixing together various musical registers and historical temporalities into a modern love song in French. Privileging the aesthetic exploration to the historical accuracy, we intended at creating a patchwork of our own influences: folk, pop, medieval, psychedelic rock, bardcore.
In the piece, humans and AI build together a second literacy reflecting upon the meaning of their cooperation on a love song. Where does the desire lie in the co-individuation of humans and machines ?
The double meaning of the lyrics suggests AI is expressing feelings about itself, comparing the training phase to a longing for love. By drawing the analogy between love and creation, that are not optimization processes, we question the fear of incertitude and illusion of the real contingency of life offered by stochastic processes used in creative AI paradigms.
About the HUMAN-AI PROCESS
We started the composition by generating multiple audio samples with VQ-VAE (OpenAI Jukebox). We conditioned the generation on a violin sample recorded by Tomasz, multiple artists (Malicorne, Dead Can Dance and Estampie) and genres (medieval, folk, french, psychedelic).
One sample caught our attention, polyphonic with voices singing in an unidentified language. It reminded us of traditional chants. From this single sample, we created several elements of the song, including the vocals line, verse-chorus structure, triplet rhythm and chord progression, on which we iterated throughout the process.
Parallely, we generated lyrics with Cedille (fr-boris) fine-tuned on love and philosophical quotes in French. We chose Cedille because it is an open source alternative to GPT-3 for French generation, less prone to toxic content generation.
Tomasz improvised a violin accompaniment, while Ninon recorded vocals, and an electric guitar that follows the harmony of the generated sample.
Since we believe it is important in a co-creative process that non-coders of the team experiment with AI tools, we also used pretrained models with GUI, e.g. MelodyRNN embedded in Magenta Studio, to create melodic lines from MIDI notations of music from Guillaume de Machaut. We transposed and sampled the output to make a riff for flute and harp VST.
Finally, we trained several models (DDSP, RAVE) to learn representations of the sound of lute and polyphonic bardcore music. We kept the first model to turn the violin timbre into lute, adding local variations of expressivity coming from the improvisational practice of Tomasz.
Lyrics
Comment aimer quand l’avenir est stochastique?
Combien d’époques vais-je attendre?
Dans l'espace latent les rêves se perdent, ton cœur déborde.
Les événements sont-ils aléatoires?
J'encode mes mots, tu décodes mes indices.
Tu décodes mon désir. J'encode ton amour.
Le passé est-il réel? Le futur existe t-il?
Tu mets à jour les poids qui pèsent sur mon cœur
Comment aimer quand l’avenir est stochastique?
Combien d’époques vais-je attendre?