eloimoliner / denoising-historical-recordingsLinks
A two-stage U-Net for high-fidelity denoising of historical recordings
☆111Updated 11 months ago
Alternatives and similar repositories for denoising-historical-recordings
Users that are interested in denoising-historical-recordings are comparing it to the libraries listed below
Sorting:
- ☆51Updated 2 years ago
- Sound Demixing Challenge 2023☆89Updated 2 years ago
- Full models and training code for PESTO☆70Updated last year
- ☆58Updated 2 years ago
- ☆85Updated 2 years ago
- AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)☆100Updated 11 months ago
- ☆52Updated last year
- Multitrack music mixing style transfer given a reference song using differentiable mixing console.☆54Updated 3 months ago
- ☆69Updated last year
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆63Updated 2 years ago
- Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems☆82Updated 3 months ago
- Implementation for "Music Enhancement via Image Translation and Vocoding"☆55Updated 3 years ago
- Headless multitrack mixing console in Python☆122Updated 2 years ago
- Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and Tensorboard features☆85Updated 2 years ago
- The official implementation of TokenSynth (ICASSP 2025)☆75Updated this week
- GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch☆131Updated 8 months ago
- ☆83Updated 2 years ago
- Audio production style transfer with inference-time optimization☆45Updated 11 months ago
- [PyTorch] Minimal codebase for MusicGen models☆63Updated 9 months ago
- Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.☆37Updated last year
- Synthesis of percussion sounds using sinusoidal modelling, DDSP noise synthesis, and a neural source filter approach.☆31Updated 9 months ago
- A project to synthesize massive amounts of multitrack audio data from MIDI.☆62Updated 5 years ago
- Differentiable dynamic range controller in PyTorch.☆51Updated last month
- Acoustic impulse response generation using diffusion models☆73Updated 2 years ago
- Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23☆120Updated 2 years ago
- End-to-end beat and downbeat tracking in the time domain.☆121Updated 3 years ago
- A DDSP-based neural voice synthesiser.☆119Updated 11 months ago
- Code for paper: "Deep Embeddings and Section Fusion Improve Music Segmentation"☆53Updated 3 years ago
- Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)☆160Updated 3 years ago
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆43Updated 5 months ago