This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Normalizing flows in PyTorch

Kolmogorov Arnold Networks

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Collection of audio-focused loss functions in PyTorch

Reduced Order Models in a scikit-learn approach.

Dingo: Deep inference for gravitational-wave observations

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

ENTERPRISE (Enhanced Numerical Toolbox Enabling a Robust PulsaR Inference SuitE) is a pulsar timing analysis code, aimed at noise analysis, gravitational-wave searches, and timing model analysis.

Acoular - Acoustic testing and source mapping software

All Algorithms implemented in Python

music demixing with the sliCQ Transform and PyTorch

PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio

Patchwork for matplotlib: A subplot manager for intuitive layouts in matplotlib, seaborn, and plotnine.

Normalising flows implemented using nflows

PyTorch implementation of the NSGT/sliCQT

Code for the paper Hybrid Spectrogram and Waveform Source Separation

A high-performance, zero-overhead, extensible Python compiler using LLVM

Python library for analysis of time series data including dimensionality reduction, clustering, and Markov model estimation

Simple Safe Sandboxed Extensible Expression Evaluator for Python

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

Noise supression using deep filtering

Official PyTorch Implementation of CleanUNet (ICASSP 2022)

Conformer-based Metric GAN for speech enhancement

The implementation of "Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement"

speech enhancement\speech seperation\sound source localization

Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

Speech Enhancement Generative Adversarial Network in TensorFlow