crlandsc / torch-log-wmseLinks
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
☆44Updated 7 months ago
Alternatives and similar repositories for torch-log-wmse
Users that are interested in torch-log-wmse are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of "Source Separation by Flow Matching (FLOSS)" by Google DeepMind☆82Updated last week
- Official Repository for "Training-Free Multi-Step Audio Source Separation"☆52Updated 6 months ago
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆41Updated 6 months ago
- Audio-to-Audio Schrodinger Bridges is a diffusion-based audio restoration model for bandwidth extension and inpainting.☆116Updated 3 months ago
- ☆45Updated last year
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆89Updated 10 months ago
- Landing Page for All Things Source Separation☆35Updated 2 months ago
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆60Updated last year
- ☆110Updated 3 months ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆66Updated 2 years ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆109Updated last year
- A DDSP-based neural voice synthesiser.☆123Updated last year
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆99Updated 4 months ago
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆44Updated 3 weeks ago
- Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23☆120Updated 2 years ago
- ☆32Updated last year
- Audiogen Codec☆142Updated last year
- Official Repository for "Music Source Restoration"☆34Updated 6 months ago
- An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation☆98Updated last year
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆99Updated last year
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆44Updated 2 years ago
- ☆84Updated 2 years ago
- Fast and accurate fundamental frequency (F0) detector using convolutional neural networks☆97Updated 3 months ago
- Baseline for DCASE 2024 Task 9: "Language-Queried Audio Source Separation"☆26Updated last year
- ☆49Updated 8 months ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆69Updated 2 years ago
- Official PyTorch implementation of "RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutiv…☆48Updated 8 months ago
- A collection of audio signals accompanied by corresponding subjective scores of perceived quality. Everything under permissive licenses.☆45Updated last year
- Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation…☆73Updated last year
- Fast and differentiable time domain all-pole filter in PyTorch.☆66Updated 2 months ago