Picture for Jan Østergaard

Jan Østergaard

Aalborg University

xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement

Add code
Jan 10, 2025
Figure 1 for xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
Figure 2 for xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
Figure 3 for xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
Figure 4 for xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
Viaarxiv icon

Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining

Add code
Jan 06, 2025
Figure 1 for Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
Figure 2 for Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
Figure 3 for Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
Figure 4 for Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
Viaarxiv icon

Room impulse response prototyping using receiver distance estimations for high quality room equalisation algorithms

Add code
Sep 16, 2024
Figure 1 for Room impulse response prototyping using receiver distance estimations for high quality room equalisation algorithms
Figure 2 for Room impulse response prototyping using receiver distance estimations for high quality room equalisation algorithms
Figure 3 for Room impulse response prototyping using receiver distance estimations for high quality room equalisation algorithms
Figure 4 for Room impulse response prototyping using receiver distance estimations for high quality room equalisation algorithms
Viaarxiv icon

The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems

Add code
Jun 10, 2024
Figure 1 for The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems
Figure 2 for The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems
Figure 3 for The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems
Figure 4 for The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems
Viaarxiv icon

Deep low-latency joint speech transmission and enhancement over a gaussian channel

Add code
Apr 30, 2024
Figure 1 for Deep low-latency joint speech transmission and enhancement over a gaussian channel
Figure 2 for Deep low-latency joint speech transmission and enhancement over a gaussian channel
Figure 3 for Deep low-latency joint speech transmission and enhancement over a gaussian channel
Figure 4 for Deep low-latency joint speech transmission and enhancement over a gaussian channel
Viaarxiv icon

How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses

Add code
Mar 15, 2024
Figure 1 for How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses
Figure 2 for How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses
Figure 3 for How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses
Figure 4 for How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses
Viaarxiv icon

Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks

Add code
Mar 15, 2024
Figure 1 for Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks
Figure 2 for Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks
Figure 3 for Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks
Figure 4 for Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks
Viaarxiv icon

Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions

Add code
Dec 27, 2023
Figure 1 for Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions
Figure 2 for Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions
Figure 3 for Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions
Figure 4 for Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions
Viaarxiv icon

Investigating the Design Space of Diffusion Models for Speech Enhancement

Add code
Dec 07, 2023
Figure 1 for Investigating the Design Space of Diffusion Models for Speech Enhancement
Figure 2 for Investigating the Design Space of Diffusion Models for Speech Enhancement
Figure 3 for Investigating the Design Space of Diffusion Models for Speech Enhancement
Figure 4 for Investigating the Design Space of Diffusion Models for Speech Enhancement
Viaarxiv icon

Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler

Add code
Dec 05, 2023
Viaarxiv icon