AudioAI

Faster, Cleaner Vocal Tracks with Latent Diffusion

Kari Jaaskelainen

26 Nov 2025 — 1 min read

Ever wanted studio‑clean vocals from any song? This research introduces a generative system that separates singing voices from full mixes using a latent diffusion model.

How it works

Generates audio in a compact latent space, then decodes it back to sound—making training and inference efficient.
Trained only on pairs of mixtures and isolated vocals (no need for every instrument stem).
Trained using open datasets.

Why it matters

Outperforms prior generative separators and matches strong non‑generative baselines on signal quality and interference removal.
Faster inference aligns with creative workflows for producers, DJs, and educators.
Noise‑robust latent encoder offers resilience in real‑world scenarios.
Released as a modular toolkit to spur further research and tooling.

Paper: https://arxiv.org/abs/2511.20470v1

Paper: https://arxiv.org/abs/2511.20470v1

Register: https://www.AiFeta.com

audioai musictech diffusionmodels sourceseparation vocals musicproduction opensource opendata latentdiffusion

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added