schufo / wiass
This is an implementation of the audio source separation model as well as the evaluation metrics proposed in the paper "Weakly Informed Audio Source Separation" by Kilian Schulze-Forster, Clement Doire, Gaël Richard, Roland Badeau. Published in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2019.
☆9Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for wiass
- ☆15Updated 2 years ago
- ☆25Updated 6 years ago
- A PyTorch implementation of the paper: "AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries" (ACM Multimedia 2021…☆20Updated 3 years ago
- melodic object transcription framework☆26Updated 6 years ago
- CANTE: Automatic transcription of flamenco singing.☆14Updated 6 years ago
- Music Demixing Challenge Submission Repo☆14Updated last year
- A duration-invariant audio-to-lyrics alignment pipeline with low memory footprint which segments long music recordings via a recursive bi…☆14Updated 2 years ago
- Zero-data (yet trainable) probabilistic fundamental frequency estimator.☆17Updated 6 years ago
- easy-to-use implementation of the ISMIR 2013 Audio Degradation Toolbox☆46Updated 4 years ago
- PyTorch implementation of the NSGT/sliCQT☆14Updated last year
- Supplemental material for the paper "Towards Automatically Correcting Tapped Beat Annotations for Music Recordings"☆20Updated 3 years ago
- A C++/Cython audio limiter for Python.☆23Updated last year
- pyMUSHRA is a python web application which hosts webMUSHRA experiments and collects the data with python.☆35Updated last year
- J-Net is aimed for audio separation with randomly weighted encoder.☆10Updated 5 years ago
- Learning Complex Basis Functions for Invariant Signal Representations with the Complex Autoencoder☆34Updated 8 months ago
- Constant-Q harmonic coefficients (CQHCs), a timbre feature designed for music signals.☆26Updated 8 months ago
- Zounds is a dataflow library for building directed acyclic graphs that transform audio. It uses the featureflow library to define the pro…☆23Updated last year
- A collection of metrics for evaluating timbre dissimilarity using the TorchMetrics API☆23Updated 2 years ago
- ☆11Updated 4 years ago
- ☆10Updated 4 years ago
- Addressing the confounds of accompaniments in singer identification☆18Updated 4 years ago
- Codebase and utilities for using models trained by multiple music related tasks☆13Updated last year
- Upsampling Artifacts in Neural Audio Synthesis – https://arxiv.org/abs/2010.14356☆76Updated 3 years ago
- ☆32Updated 3 years ago
- Supplementary code for the experiments described in the 2021 ISMIR submission: Leveraging Hierarchical Structures for Few Shot Musical In…☆40Updated 2 years ago
- Reproducible Subjective Evaluation☆57Updated 8 months ago
- Streaming source separation for music and speech files, using the Open-Unmix LSTM architecture.☆17Updated last year
- Unsupervised Representation Learning for Singing Voice Separation☆21Updated last year
- Python bindings for SoX, aiming to replicate a subset of the command line sox utility.☆52Updated 3 years ago
- SDX23 startkit for the Demucs baselines.☆24Updated last year