Aiksier

pykan

Kolmogorov Arnold Networks

DPMTSE

A Diffusion Probabilistic Model for Target Sound Extraction

CLAPSep

Query-conditioned target sound extraction model

espnet

End-to-End Speech Processing Toolkit

asteroid

Pytorch-based audio source separation toolkit || Current highlight : the new recipe for Microsoft's DNS Challenge !

uss

asteroid

The PyTorch-based audio source separation toolkit for researchers

Meta

Fast Adaptive Active Noise Control based on Modified Model-Agnostic Meta-Learning Algorithm

Speech-Separation-Paper-Tutorial

A must-read paper for speech separation based on neural networks

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

NUMBA-Accelerated-Wave-Domain-Spatial-Active-Noise-Control

This repository includes an implementation of the normalised LMS method of Wave Domain Spatial Active Noise Control which was accelerated with both NUMBA's C-JIT functionality and its CUDA-JIT functionality. It was created so that the linear and parallel compute performance of this algorithm could be compared.

SemanticHearing

Real-time binaural target sound extraction model.

thesisuestc

ThesisUESTC-电子科技大学毕业论文模板

spikingjelly

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

bindsnet

Simulation of spiking neural networks (SNNs) using PyTorch.

Spiking-Neural-Network-SNN-with-PyTorch-where-Backpropagation-engenders-STDP

What about coding a Spiking Neural Network using an automatic differentiation framework? In SNNs, there is a time axis and the neural network sees data throughout time, and activation functions are instead spikes that are raised past a certain pre-activation threshold. Pre-activation values constantly fades if neurons aren't excited enough.

sudo_rm_rf

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.

Waveformer

A deep neural network architecture for low-latency audio processing

ChatPaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

TCN

Sequence modeling benchmarks and temporal convolutional networks

CAT

A CRF-based ASR Toolkit

speechbrain

A PyTorch-based Speech Toolkit

FullSubNet

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

AudioAutoencoder

My experiments with audio autoencoder using mel spectrograms

mobilenetv3

mobilenetv3 with pytorch，provide pre-train model

cpjku_dcase20

CP-JKU submission to DCASE 20

SFANC-FxNLMS-ANC-Algorithm-based-on-Deep-Learning

This paper proposes a hybrid SFANC-FxNLMS approach to overcome the adaptive algorithm's slow convergence and provide a better noise reduction level than the SFANC method.

AD-YOLO

AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection, ICASSP 2023

mtan

The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].

voice_datasets

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).