#neuralaudio

MARTSM_N /// martsmanmartsm_n
2025-04-10

I've written a set of abstractions that initially were supposed to store banks of offset values in order to make longer compositions with RAVE and vschaos2 models possible.
Eventually these became tools to move smoothly through latent space by adding simple multichannel modulation on top.
Here's a recording of a setup where these abstractions are used on one of my recently trained model 'Nobrowski'.

youtube.com/watch?v=WPD6z3g0lSk

MARTSM_N /// martsmanmartsm_n
2024-12-18

Some experiments with slow sequencing through arbitrary value patterns into signal generators in latent space of two vschaos2 models - one is trained on a selection of music, the other is based on voice recordings. youtu.be/c-CPHIKseNk?feature=s

MARTSM_N /// martsmanmartsm_n
2024-11-16

VARIA 3L is an improvisation session recording from semi-generative framework "Saatgut Proxy 2 (Varia)" written in

The framework creates both randomized and repeatable pathways through the latent space of two model-architectures (RAVE, vschaos2). The models used for this recording have been trained on the author’s musical body of work.

ninaprotocol.com/releases/mart

VARIA 3L release artwork
MARTSM_N /// martsmanmartsm_n
2024-09-28

Latent Jamming in "Saatgut Proxy", an experimental generative setup implemented in that works with two model architectures: and vschaos2. youtu.be/EdpGwXH5nr0

MARTSM_N /// martsmanmartsm_n
2024-09-22

In this video, I'm showcasing the patch and configuration that led to track "Tritt Nochmal Zu" from my Saatgut Proxy/ Saatgut Proxy Reflux release in late 2023/ early 2024. The patch contains a setup of vschaos2 and RAVE model decoder layers and predefined seeds for mocking latent embeddings.
The models have been trained on a dataset selected from my own release material.
youtube.com/watch?v=iij0bDvEMRI

MARTSM_N /// martsmanmartsm_n
2024-09-22

Neural audio latent seeding with Saatgut component in using custom data (Martsman material) trained model youtube.com/watch?v=3QMDmU0dtIM

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst