Ai
Projets
-
Project
Bucolic by Vasileios Agiomyrgianakis, Haruka Hirayama, Jussi Tuohino, Osmo Hakosalo
Proposal type: demo Themes: Real-time technologies, sound synthesis, AI & music Title: Cultural Machines: Embodied Interaction with Robotic Traditi…
-
Project
RAVE
RAVE is an audio processing/generativity based on deep learning. RAVE (Realtime Audio Variational autoEncoder) is a learning framework for generating…
-
Project
vschaos2
vschaos2, based on the original 2019 vschaos package, is a vintage-flavoured neural audio synthesis package. It is based on unsupervised / (semi-)sup…
-
Project
Imagine Sound! Where Your Images Revived 🎶
Imagine Sound! Where Your Images Revived, a groundbreaking application brought to you by Bilsimaging. Dive into a world where your images are not j…
-
Project
Music to Image Interpolation
Generative AI pipeline that produces image interpolations from an audio track, leveraging Stable Diffusion technology.
-
Project
Autoencoder for Max
This repository contains a compiled external and examples for loading models trained for the Autocoder, an implementation of a variational autoencode…
-
Project
RAVE-audition
VST/AU Plugin for Auditioning RAVE Models in Real-time
-
Project
WaVAE
Realtime Variational Autoencoder built on top of libtorch and PureData
-
Project
OM-DYCI2
DYCI2 objects for learning-based generative processes in the OM/OM# visual programming environment
-
Project
Flow Synthetizer
Sound synthesizers are pervasive in music and they now even entirely define new music genres. However, their complexity and sets of parameters render…
-
Project
FCN-F0
Code for running monophonic pitch (F0) estimation using the fully-convolutional neural network models described in the publication : L. Ardaillon …
-
Project
DDSP
Differentiable Digital Signal Processing. Implementation of the DDSP model using PyTorch. This implementation can be exported to a torchscript model,…
Articles
-
Article
AudioStellar, an open source corpus-based musical instrument for latent sound structure discovery and sonic experimentation by Agustin Spinetto
AudioStellar is a free experimental sampler that uses AI to generate a 2D point map from a folder with audio samples. The sounds included in the map …
-
Article
Somax 2 Tutorials
Cette page rassemble des tutoriels vidéo sur Somax2.
-
Article
Fragments 1-11 by Yun Park & Jeanyoon Choi
《Fragments 1-11》 explores how AI opens a new paradigm of artistic creation in the era of generative AI. This exhibition demonstrates a multidimension…
-
Article
Tutorial: Neural Synthesis in Max 8 with RAVE
Learn to perform neural audio synthesis inside Max 8 using nn~.
-
Article
Somax version 2.7.0 is out!
This version introduces Max 9 compatibility, a redesigned user interface, multi-label corpus building, and new label handling for filtering and real-…
-
Article
Artaud & AI by Lionel Hubert
“Artaud and AI” stages a radical encounter between the wild, visceral voice of Antonin Artaud and the rational structures of artificial intelligence.…
-
Article
'Points of Articulation: Machine learning, speech synthesis and vocal music' by Seth Scott.
A presentation on composing vocal music using AI-powered speech synthesis technologies.
-
Article
Tutorial: Training RAVE models on custom data
Learn to train RAVE models on custom data.
-
Article
Sound, data, and the creation of the virtual space
With the advancement of AI, technologies like Muse and ACE are transforming the creation of virtual worlds. This raises the question: How will AI aff…
-
Article
Tutorial: Neural Synthesis in a DAW with RAVE
Learn to perform neural audio synthesis inside your favorite digital audio workstation with RAVE.
-
Article
Latent Terrain: Dissecting the Latent Space of Neural Audio Autoencoders by Shuoyang Jasper Zheng
Exploring musical affordances of neural networks beyond their task-oriented capabilities and deriving sonic materials for musical expressions.
-
Article
Le corps du corpus. Embodied Interaction From Machine-Learning In Human-Machine Improvisation (Interaction incarnée à partir de l'apprentissage automatique dans l'improvisation homme-machine).
L'article de Pierre Saint-Germier, Clément Canonne et Marco Fiorini a été accepté pour la conférence AIMC2024 (The International Conference on AI and…
-
Article
Somax 2.6 et les outils de co-création REACH - Marco Fiorini, Mikhail Malt
Présentation de la dernière version de Somax 2.6 et des outils de co-création du projet REACH en cours de développement, lors des Ateliers du Forum I…
Collections
-
Collection
RAVE
RAVE is an audio processing/generativity based on deep learning. RAVE (Realtime Audio Variational autoEncoder) is a learning framework for generating…