Skip to content

@sp-uhh Signal Processing (SP), Universität Hamburg

Change the repository type filter

All

    Repositories list

    29 repositories

    • gen-se-demo

      Public
      Diffusion-based Speech Enhancement: Demonstration of Performance and Generalization
      Jupyter Notebook
      •
      MIT License
      •2•5•0•0•Updated Dec 21, 2024Dec 21, 2024

    • sgmse

      Public
      Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
      Python
      •
      MIT License
      •76•541•10•0•Updated Dec 21, 2024Dec 21, 2024

    • group_affect

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Dec 19, 2024Dec 19, 2024

    • gen-se

      Public
      Investigating Training Objectives for Generative Speech Enhancement
      HTML
      •0•3•0•0•Updated Dec 11, 2024Dec 11, 2024

    • 2sderev

      Public
      Two-stage Dereverberation Algorithm using DNN-supported multi-channel linear filtering and single-channel non-linear post-filtering
      Python
      •2•3•0•0•Updated Oct 21, 2024Oct 21, 2024

    • buddy

      Public
      BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
      Python
      •4•37•1•0•Updated Oct 18, 2024Oct 18, 2024

    • ears_dataset

      Public
      HTML
      •0•2•0•0•Updated Sep 24, 2024Sep 24, 2024

    • ears_benchmark

      Public
      Generation scripts for EARS-WHAM and EARS-Reverb
      Python
      •3•27•0•0•Updated Sep 16, 2024Sep 16, 2024

    • storm

      Public
      StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
      Python
      •
      MIT License
      •26•195•2•0•Updated Sep 13, 2024Sep 13, 2024

    • website_template

      Public
      HTML
      •0•0•0•0•Updated Jun 25, 2024Jun 25, 2024

    • sp-uhh.github.io

      Public
      HTML
      •0•0•0•0•Updated Apr 24, 2024Apr 24, 2024

    • driftrec

      Public
      DriftRec: Adapting diffusion models to blind image restoration tasks
      Python
      •0•4•2•0•Updated Feb 23, 2024Feb 23, 2024

    • deep-non-linear-filter

      Public
      Python
      •14•50•2•1•Updated Feb 9, 2024Feb 9, 2024

    • derevdps

      Public
      Python
      •1•13•1•0•Updated Jan 12, 2024Jan 12, 2024

    • sgmse_crp

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •2•21•1•0•Updated Jan 9, 2024Jan 9, 2024

    • sgmse-bbed

      Public
      TODO
      Python
      •
      MIT License
      •8•37•1•1•Updated Nov 1, 2023Nov 1, 2023

    • livepty

      Public
      Live Iterative Ptychography with projection-based algorithms
      Python
      •
      GNU General Public License v3.0
      •0•3•0•0•Updated Sep 21, 2023Sep 21, 2023

    • diffphase

      Public
      DiffPhase: Generative Diffusion-based STFT Phase Retrieval
      Python
      •
      MIT License
      •0•11•0•0•Updated Sep 21, 2023Sep 21, 2023

    • label-uncertainty-ser

      Public
      Python
      •
      MIT License
      •2•5•0•0•Updated Jun 6, 2023Jun 6, 2023

    • uncertainty-SE

      Public
      Python
      •
      MIT License
      •0•15•1•0•Updated Mar 30, 2023Mar 30, 2023

    • av-phoneme

      Public
      Continous Phoneme Recognition based on Audio-Visual Modality Fusion
      Python
      •
      MIT License
      •1•2•0•0•Updated Jul 23, 2022Jul 23, 2022

    • disentangled-vae

      Public
      Repository for the paper "Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement".
      Python
      •2•6•1•0•Updated Aug 30, 2021Aug 30, 2021

    • audio-visual-vad

      Public
      Re-implementation of the paper "An End-to-End Multimodal Voice Activity Detection Using WaveNet Encoder and Residual Networks"
      Python
      •1•6•0•0•Updated Aug 3, 2021Aug 3, 2021

    • WSJ0-mixK-Dataset-Creation

      Public
      MATLAB
      •
      MIT License
      •0•4•0•0•Updated May 29, 2021May 29, 2021

    • guided-vae-nmf

      Public
      This is the repository of the paper
      Jupyter Notebook
      •0•8•0•0•Updated May 7, 2021May 7, 2021

    • stcn-nmf

      Public
      VAE and STCN with NMF for single-channel speech enhancement
      Python
      •
      MIT License
      •4•14•0•0•Updated Mar 24, 2021Mar 24, 2021

    • compressed-lstm

      Public
      Compressed Long Short-Term Memory (CLSTM) Keras Layer
      Python
      •
      Other
      •0•0•0•0•Updated Nov 22, 2020Nov 22, 2020

    • dual-path-rnn

      Public
      Dual-Path RNN for Single-Channel Speech Separation (in Keras-Tensorflow2)
      Python
      •
      MIT License
      •6•34•2•0•Updated Jun 2, 2020Jun 2, 2020

    • mp-gtf

      Public
      Multi-Phase Gammatone Filterbank (MP-GTF) construction for Python
      Python
      •
      Other
      •7•46•3•0•Updated Apr 30, 2020Apr 30, 2020