sp-uhh/dual-path-rnn

Stars
34
Rank 762,775 (Top 16 %)
Language
Python
License
MIT License
Created almost 5 years ago
Updated over 4 years ago

sp-uhh/dual-path-rnn

sp-uhh

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Dual-Path RNN for Single-Channel Speech Separation (in Keras-Tensorflow2)

sgmse

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation

storm

StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation

mp-gtf

Multi-Phase Gammatone Filterbank (MP-GTF) construction for Python

deep-non-linear-filter

buddy

BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models

sgmse-bbed

uncertainty-SE

stcn-nmf

VAE and STCN with NMF for single-channel speech enhancement

sgmse_crp

derevdps

diffphase

DiffPhase: Generative Diffusion-based STFT Phase Retrieval

ears_benchmark

Generation scripts for EARS-WHAM and EARS-Reverb

guided-vae-nmf

This is the repository of the paper

Jupyter Notebook

audio-visual-vad

Re-implementation of the paper "An End-to-End Multimodal Voice Activity Detection Using WaveNet Encoder and Residual Networks"

disentangled-vae

Repository for the paper "Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement".

driftrec

DriftRec: Adapting diffusion models to blind image restoration tasks

WSJ0-mixK-Dataset-Creation

label-uncertainty-ser

livepty

Live Iterative Ptychography with projection-based algorithms

av-phoneme

Continous Phoneme Recognition based on Audio-Visual Modality Fusion

ears_dataset

2sderev

Two-stage Dereverberation Algorithm using DNN-supported multi-channel linear filtering and single-channel non-linear post-filtering