merlresearch / hyper-unmix
Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation.”
☆57Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hyper-unmix
- Pytorch implementation of subband decomposition☆89Updated 2 years ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆54Updated last year
- An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation☆81Updated 8 months ago
- ☆43Updated 3 weeks ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆72Updated 2 months ago
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆60Updated last year
- PyTorch Dataset for Speech and Music audio☆73Updated 4 months ago
- ☆79Updated last year
- This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBER…☆27Updated 2 years ago
- Translating Synthetic RIRs to Real RIRs☆40Updated last year
- Da - ECHO - RetrievAl - daTasEt☆24Updated 4 months ago
- ☆59Updated last year
- PAM is a no-reference audio quality metric for audio generation tasks☆49Updated 4 months ago
- Unsupervised Representation Learning for Singing Voice Separation☆21Updated last year
- PodcastMix A dataset for separating music and speech in podcasts.☆43Updated 3 months ago
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- Backpropagable pytorch implementation of https://craffel.github.io/mir_eval/.☆35Updated 4 months ago
- Implementation for "Music Enhancement via Image Translation and Vocoding"☆52Updated 2 years ago
- ☆40Updated 5 months ago
- ☆49Updated last year
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆45Updated 7 months ago
- This code is to run the WARP-Q speech quality metric.☆34Updated last month
- ☆47Updated last week
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆20Updated 11 months ago
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆69Updated last month
- ☆64Updated last year
- ☆51Updated last month
- logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even whe…☆33Updated 2 months ago
- NOMAD: Non-Matching Audio Distance (ICASSP 2024)☆24Updated last month
- ☆28Updated last year