KyungsuKim42 / tokensynthLinks
The official implementation of TokenSynth (ICASSP 2025)
☆78Updated 3 months ago
Alternatives and similar repositories for tokensynth
Users that are interested in tokensynth are comparing it to the libraries listed below
Sorting:
- Encode and decode audio samples to/from continuous and discrete compressed representations!☆100Updated 2 months ago
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆46Updated last year
- [PyTorch] Minimal codebase for MusicGen models☆63Updated last year
- Audio production style transfer with inference-time optimization☆49Updated last year
- Compute distribution-based quality metrics for audio data using embeddings, with a focus on music.☆43Updated 3 weeks ago
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆62Updated 11 months ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆45Updated 2 years ago
- ☆87Updated 3 years ago
- Polyphonic generalisation of DDSP☆22Updated last year
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆69Updated 3 years ago
- A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating …☆93Updated 7 months ago
- A DDSP-based neural voice synthesiser.☆126Updated last year
- JamendoMaxCaps is a large-scale dataset of 362,000 instrumental creative commons tracks☆45Updated 8 months ago
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆29Updated 3 years ago
- ☆68Updated last year
- Training, validation, and inference code for various SSL approaches and architectures.☆77Updated 3 months ago
- Full models and training code for PESTO☆74Updated last year
- Multitrack music mixing style transfer given a reference song using differentiable mixing console.☆55Updated 6 months ago
- Synthesis of percussion sounds using sinusoidal modelling, DDSP noise synthesis, and a neural source filter approach.☆31Updated last year
- Chorale Music Separation Dataset and Model Framework☆40Updated 3 years ago
- Code for the paper "Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription"☆40Updated last year
- Github repository for the paper accepted in ICASSP 2024 : Blind estimation of audio effects using an auto-encoder approach and differenti…☆14Updated last year
- Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.☆39Updated last year
- Official repository for Aria-MIDI: a MIDI dataset of 1,186,253 transcribed solo-piano recordings.☆72Updated 7 months ago
- Differentiable dynamic range controller in PyTorch.☆52Updated 3 weeks ago
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆26Updated 2 months ago
- MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.☆44Updated last year
- ☆29Updated 2 years ago
- Code for the paper "Toward Fully Self-Supervised Multi-Pitch Estimation".☆23Updated 4 months ago
- Estimating musical surprisal/information content in Audio☆21Updated 2 weeks ago