sai-soum / Diff-MSTLinks
Multitrack music mixing style transfer given a reference song using differentiable mixing console.
☆50Updated last week
Alternatives and similar repositories for Diff-MST
Users that are interested in Diff-MST are comparing it to the libraries listed below
Sorting:
- Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.☆37Updated 11 months ago
- MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage☆44Updated 11 months ago
- ☆56Updated 7 months ago
- A Jupyter book accompanying the ISMIR 2023 tutorial Introduction to DIfferentiable Audio Synthesiser Programming☆57Updated last year
- Full models and training code for PESTO☆66Updated last year
- Audio production style transfer with inference-time optimization☆40Updated 7 months ago
- Frechet Audio Distance evaluation in PyTorch☆36Updated 2 years ago
- ☆83Updated 2 years ago
- ☆58Updated 3 weeks ago
- Official Implementation of Jointist☆35Updated last year
- Polyphonic generalisation of DDSP☆19Updated last year
- PyTorch version of Spotify's Basic Pitch☆39Updated last year
- The official implementation of TokenSynth (ICASSP 2025)☆70Updated last month
- Synthesis of percussion sounds using sinusoidal modelling, DDSP noise synthesis, and a neural source filter approach.☆29Updated 5 months ago
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆49Updated 4 months ago
- ☆18Updated last year
- ☆17Updated 7 months ago
- GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch☆125Updated 4 months ago
- Differentiable dynamic range controller in PyTorch.☆49Updated 6 months ago
- A piano music dataset with Audio, Symbolic and Text labels☆28Updated 3 months ago
- Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems☆64Updated 7 months ago
- Code for the paper "Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription"☆39Updated last year
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆20Updated 4 months ago
- list of MIR dataset papers presented at ISMIR 2022☆61Updated 2 years ago
- ☆30Updated 2 weeks ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆42Updated 2 years ago
- DExter: Learning and Controlling Performance Expression through Diffusion models☆16Updated 11 months ago
- [PyTorch] Minimal codebase for MusicGen models☆61Updated 5 months ago
- Code accompayning ISMIR23 paper; TriAD: Capturing harmonics with 3D convolutions☆17Updated 11 months ago
- ☆49Updated last year