gedebabin Goto Github PK

adsp_tutorials

Advanced Signal Processing Notebooks and Tutorials

auraloss

Collection of audio-focused loss functions in PyTorch

av-e3net

awesome-speech-enhancement-1

speech enhancement\speech seperation\sound source localization

bs-roformer

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

causal-conv1d

Causal depthwise conv1d in CUDA, with a PyTorch interface

cmgan

Conformer-based Metric GAN for speech enhancement

codellama

Inference code for CodeLlama models

coder2gwy

互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

cpp_inference_crn

C++实现CRN前向推理

darcn

The implementation of "A Recursive Network with Dynamic Attention for Monaural Speech Enhancement"

db-aiat

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

dbt-net

The audio demos with respect to the paper "DBT-Net: Dual-branch federative magnitude and phase estimation with attention-in-attention transformer for monaural speech enhancement" are provided (submitted to TASLP). The code will also be released soon.

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

deepcomplexcrn

deepfilternet

Noise supression using deep filtering

deepvqe

An unofficial implementation of DeepVQE proposed by Microsoft Corp.

dns_mos_calculate

Code for calculate DNS_MOS.

dparn

dpcrn_dns3

Implementation of paper "DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement"

dpmtse

dttnet-pytorch

An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation

ecapa-tdnn

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

eend-iaae

The implementation of "End-to-End Neural Speaker Diarization with an Iterative Adaptive Attractor Estimation", which is accepted by Neural Networks.

exarn-target-speaker-extraction-with-attentive-recurrent-networks

fft-conv-pytorch

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

fnse-sat

fqse

Fully Quantized Neural Networks For Speech Enhancement

fra-rir

fullsubnet-plus

The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".