happlydata's repositories
Speech-Separation-Paper-Tutorial
A must-read paper for speech separation based on neural networks
Tacotron2-PyTorch
Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.
HGCN
The official repo of "HGCN: Harmonic Gated Compensation Network For Speech Enhancement"
CMGAN
Conformer-based Metric GAN for speech enhancement
FullSubNet-plus
The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".
CDEC
Cross-Domain Echo Controller
AEC3
AEC3 Extracted From WebRTC
MusicYOLO
MusicYOLO framework uses the object detection model, YOLOx, to locate notes in the spectrogram.
DeepFilterNet
Noise supression using deep filtering
DB-AIAT
A dual-branch attention-in-attention transformer (dubbed DB-AIAT) to focus on both coarse and fine-grained regions of spectrum in parallel, i.e., spectral magnitude and lost complex spectral details. The source code will be released soon
pyaec
simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link adaptive filters)、frequency domain adaptive filters(frequency domain adaptive filter、frequency domain kalman filter) for acoustic echo cancellation.
speechbrain
A PyTorch-based Speech Toolkit
midi_degradation_toolkit
A toolkit for generating datasets of midi files which have been degraded to be 'un-musical'.
wavebeat
End-to-end beat and downbeat tracking in the time domain.
LibriMix
An open source dataset for source separation
LibtorchTutorials
This is a code repository for pytorch c++ (or libtorch) tutorial.
voice-activity-detection
Pytorch implementation of SELF-ATTENTIVE VAD, ICASSP 2021
kissfft
a Fast Fourier Transform (FFT) library that tries to Keep it Simple, Stupid
autodsp
Train custom adaptive filter optimizers without hand tuning or extra labels.
Complex_PF
RES via complex-valued DNN
segan
Speech Enhancement Generative Adversarial Network in TensorFlow
NRES
Neural Residual Echo Suppressor
specmix
This is a project of Interspeech2021 paper "SpecMix : A Mixed Sample Data Augmentation method for Training with Time-Frequency Domain Features"
TSEGAN
The implement of the paper 'Time-domain Speech Enhancement with GenerativeAdversarial Learning'
DSDPRNN
Implementation of Dual-Stream DPRNN (paper: Nonlinear Residual Echo Suppression Based on Dual-Stream DPRNN)
VAD
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
rnnoise_16k
implementation of rnnoise_16k