This is the source code for the experiments related to the paper Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

Last update: Oct 19, 2022

Related tags

Deep Learning umss

Overview

Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

This is the source code for the experiments related to the paper Unsupervised Audio Source Separation Using Differentiable Parametric Source Models.

It contains a re-implementation of parts of the DDSP library in PyTorch. We added a differentiable all-pole filter which can be parameterized by line spectral frequencies or reflection coefficients.

Please cite the paper, if you use parts of the code in your work.

Links

🔊 Audio examples

📄 Paper

Requirements

The following packages are required:

pytorch==1.6.0
matplotlib==3.3.1
python-sounddevice==0.4.0
scipy==1.5.2
torchaudio=0.6.0
tqdm==4.49.0
pysoundfile==0.10.3
librosa==0.8.0
scikit-learn==0.23.2
tensorboard==2.3.0
resampy==0.2.2
pandas==1.2.3
tensorboard==2.3.0

Training

python train.py -c config.txt

python train_u_nets.py -c unet_config.txt

Evaluation

python eval.py --tag 'TAG' --f0-from-mix --test-set 'CSD'

Acknowledgment

This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 765068.

This is the source code for the experiments related to the paper Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

Related tags

Overview

Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

Links

Requirements

Training

Evaluation

Acknowledgment

Copyright

Owner

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

HDMapNet: A Local Semantic Map Learning and Evaluation Framework

The modify PyTorch version of Siam-trackers which are speed-up by TensorRT.

Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

Anomaly detection in multi-agent trajectories: Code for training, evaluation and the OpenAI highway simulation.

A Deep Learning based project for creating line art portraits.

Graph WaveNet apdapted for brain connectivity analysis.

G-NIA model from "Single Node Injection Attack against Graph Neural Networks" (CIKM 2021)

Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord.

I-SECRET: Importance-guided fundus image enhancement via semi-supervised contrastive constraining

Codes for "Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier"

Time Series Cross-Validation -- an extension for scikit-learn

PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML)

Codes for "CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation"

AI drive app that can help user become beautiful.

LocUNet is a deep learning method to localize a UE based solely on the reported signal strengths from a set of BSs.

Code for the paper "Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds" (ICCV 2021)

Code for "Layered Neural Rendering for Retiming People in Video."

Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

The codebase for our paper "Generative Occupancy Fields for 3D Surface-Aware Image Synthesis" (NeurIPS 2021)