Open to contributions to make this framework bigger and better.

🙏 Thanks to my collaborators @csteinmetz1.bsky.social and Joshua Reiss.

Differentiable DSP processors and controllers for non-parametric and parametric signal chains.

State-of-the-art neural networks and conditioning methods for audio effects modeling.

NablAFx includes all necessary classes to train a model, plot and log losses, metrics and media.

Compared to other frameworks/libraries, NablAFx includes all the building blocks to define, train and evaluate black-box models or gray-box signal chains.

GitHub - mcomunita/nablafx: Framework for differentiable black-box and gray-box audio effects modeling Framework for differentiable black-box and gray-box audio effects modeling - mcomunita/nablafx

We open-sourced NablAFx. A Framework for differentiable black-box and gray-box audio effects modeling.

Nabla (∇) + Audio Effects (AFx) = NablAFx [∇f(x)]

📜: arxiv.org/abs/2502.11668
💻: github.com/mcomunita/na...

GitHub - mcomunita/webMUSHRA-frontend: a better documented version of webMUSHRA a better documented version of webMUSHRA. Contribute to mcomunita/webMUSHRA-frontend development by creating an account on GitHub.

If you - like me - are not great with web dev and you need to setup an online listening test...I made a 𝒃𝒆𝒕𝒕𝒆𝒓 𝒅𝒐𝒄𝒖𝒎𝒆𝒏𝒕𝒆𝒅 𝒘𝒆𝒃𝑴𝑼𝑺𝑯𝑹𝑨 to guide you step-by-step.

github.com/mcomunita/we...

Help us with our research to:
☝️ - Develop a perceptual similarity metric for audio effects
✌️ - Advance the state of the art in audio effects modelling Take our listening test (<15min): mcomunita.github.io/mushra-front...
Use: 💻 + 🎧

🙏

Stable-V2A: Synchronized Sound Effects Synthesis Stable-V2A is a two-stage model for synthesizing synchronized sound effects with support for temporal and semantic controls.

🌟 Excited to Share Our Latest Work! 🎥🎶

Here we present Stable-V2A: Synthesis of Synchronized Sound Effects with Temporal and Semantic Controls

arxiv: arxiv.org/abs/2412.15023
Video presentation and results: ispamm.github.io/Stable-V2A

new paper! 🗣️Sketch2Sound💥

Sketch2Sound can create sounds from sonic imitations (i.e., a vocal imitation or a reference sound) via interpretable, time-varying control signals.

paper: arxiv.org/abs/2412.08550
web: hugofloresgarcia.art/sketch2sound

Would love to be added! Thanks for this list.