julius-richter

PhD student at Universität Hamburg working on deep generative models for speech enhancement.

Hamburg, Berlin

Pinned Repositories

nevergrad
A Python toolbox for performing gradient-free optimization
Language:Python4k 58 266356
beat_tracker
Style-specific beat tracking with deep neural networks
Language:Jupyter Notebook30 1 25
nevergrad
A Python toolbox for performing gradient-free optimization
Language:Python0 1 00
sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
Language:Python1 1 01
stcn-nmf
VAE and STCN with NMF for single-channel speech enhancement
Language:Python0 1 00
SEMamba
This is the official implementation of the SEMamba paper. (Accepted to IEEE SLT 2024)
Language:Python154 12 2015
av-phoneme
Continous Phoneme Recognition based on Audio-Visual Modality Fusion
Language:Python2 2 01
gen-se-demo
Diffusion-based Speech Enhancement: Demonstration of Performance and Generalization
Language:Jupyter Notebook52
sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
Language:Python548 13 6177
stcn-nmf
VAE and STCN with NMF for single-channel speech enhancement
Language:Python14 2 04

julius-richter/beat_tracker
Style-specific beat tracking with deep neural networks
Language:Jupyter Notebook30 1 25
julius-richter/sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
Language:Python1 1 01
julius-richter/nevergrad
A Python toolbox for performing gradient-free optimization
Language:Python0 1 00
julius-richter/stcn-nmf
VAE and STCN with NMF for single-channel speech enhancement
Language:Python0 1 00