YoonjinXD / kadtk
A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating generative audio.
☆65Updated 3 weeks ago
Alternatives and similar repositories for kadtk:
Users that are interested in kadtk are comparing it to the libraries listed below
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆59Updated 2 years ago
- The official implementation of TokenSynth (ICASSP 2025)☆65Updated last month
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆46Updated last month
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆41Updated last year
- Polyphonic generalisation of DDSP☆18Updated 11 months ago
- [PyTorch] Minimal codebase for MusicGen models☆58Updated 3 months ago
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆45Updated 6 months ago
- ☆43Updated 10 months ago
- ☆55Updated 5 months ago
- A DDSP-based neural voice synthesiser.☆115Updated 5 months ago
- A pretrained model for "A Phoneme-informed Neural Network Model for Note-level Singing Transcription", ICASSP 2023☆30Updated last year
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆30Updated 3 months ago
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆22Updated last year
- ☆52Updated last year
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆41Updated 2 months ago
- ☆81Updated 2 years ago
- ☆29Updated this week
- ☆20Updated 2 months ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆50Updated last year
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metri…☆33Updated last month
- ☆28Updated last year
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆28Updated 2 years ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆64Updated last year
- Project for MIDI to Audio Synthesis☆23Updated 2 years ago
- This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBER…☆30Updated 2 years ago
- A piano music dataset with Audio, Symbolic and Text labels☆27Updated last month
- Robust Singing Voice Transcription and MIDI Extraction☆73Updated 4 months ago
- Official Implementation of Jointist☆33Updated last year
- Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"☆55Updated 4 months ago