nomonosound / log-wmse-audio-quality
logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even when there are many audio tracks or stems.
☆34Updated 6 months ago
Alternatives and similar repositories for log-wmse-audio-quality:
Users that are interested in log-wmse-audio-quality are comparing it to the libraries listed below
- A fast python library for aligning similar audio snippets passed in as NumPy arrays☆44Updated this week
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆27Updated 3 months ago
- Project for MIDI to Audio Synthesis☆22Updated 2 years ago
- Fast and differentiable time domain all-pole filter in PyTorch.☆57Updated last month
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆40Updated last year
- Differentiable dynamic range controller in PyTorch.☆47Updated 3 months ago
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆37Updated 4 months ago
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- ☆22Updated 6 months ago
- Official repository for the paper "Audio xLSTMs: Learning Self-supervised audio representations with xLSTMs"☆14Updated 6 months ago
- PodcastMix A dataset for separating music and speech in podcasts.☆43Updated 7 months ago
- ☆17Updated 3 years ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆58Updated 2 years ago
- Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.☆36Updated 8 months ago
- Polyphonic generalisation of DDSP☆18Updated 10 months ago
- ☆43Updated 9 months ago
- Reproducible Subjective Evaluation☆59Updated last year
- A C++/Cython audio limiter for Python.☆25Updated 2 years ago
- logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source…☆36Updated 7 months ago
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆22Updated last year
- ☆22Updated 11 months ago
- pyMUSHRA is a python web application which hosts webMUSHRA experiments and collects the data with python.☆43Updated last year
- Baseline for DCASE 2024 Task 9: "Language-Queried Audio Source Separation"☆24Updated 11 months ago
- ☆26Updated this week
- Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"☆55Updated 4 months ago
- An open source platform for browser based speech and audio subjective quality tests.☆33Updated last year
- Pytorch implementation of the invertible CQT based on Non-stationary Gabor filters☆29Updated last year
- libsoni: A Python Toolbox for Sonifying Music Annotations and Feature Representations☆20Updated last week