crlandsc / torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
☆36Updated 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
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆57Updated 2 years ago
- ☆43Updated 9 months ago
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆36Updated 3 months ago
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆52Updated 11 months ago
- ☆22Updated 10 months ago
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆22Updated last year
- Bandwidth Extension of Historical Recordings using Generative Adversarial Networks☆35Updated last year
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆27Updated 2 months ago
- This is the official implementation of our multi-channel multi-speaker multi-spatial neural audio codec architecture.☆46Updated 6 months ago
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆62Updated last year
- A DDSP-based neural voice synthesiser.☆113Updated 4 months ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆64Updated last year
- Code for the paper "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆55Updated last month
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆40Updated last year
- Full models and training code for PESTO☆60Updated 9 months ago
- logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even whe…☆34Updated 6 months ago
- ☆51Updated last year
- ☆22Updated 6 months ago
- Fast and differentiable time domain all-pole filter in PyTorch.☆56Updated last month
- PAM is a no-reference audio quality metric for audio generation tasks☆57Updated 7 months ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆50Updated last year
- AudioSR-Upsampling (any -> 48kHz)☆40Updated last year
- Transformer with Local Modeling by Convolution for Speech Separation and Enhancement☆47Updated 7 months ago
- code for "DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper"☆23Updated 11 months ago
- ☆85Updated 2 months ago
- ☆63Updated 11 months ago
- Differentiable Mean Opinion Score Regularization for Perceptual Speech Enhancement☆22Updated last year