Alert button
Picture for Bernd Edler

Bernd Edler

Alert button

SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement

Dec 04, 2023
Martin Strauss, Nicola Pia, Nagashree K. S. Rao, Bernd Edler

Viaarxiv icon

Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio

May 31, 2023
Luca Resti, Martin Strauss, Matteo Torcoli, Emanuël Habets, Bernd Edler

Figure 1 for Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio
Figure 2 for Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio
Figure 3 for Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio
Figure 4 for Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio
Viaarxiv icon

A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain

Jan 28, 2022
Kishan Gupta, Srikanth Korse, Bernd Edler, Guillaume Fuchs

Figure 1 for A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
Figure 2 for A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
Figure 3 for A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
Figure 4 for A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
Viaarxiv icon

A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation

Jun 22, 2021
Martin Strauss, Jouni Paulus, Matteo Torcoli, Bernd Edler

Figure 1 for A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation
Figure 2 for A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation
Viaarxiv icon

A Hands-on Comparison of DNNs for Dialog SeparationUsing Transfer Learning from Music Source Separation

Jun 16, 2021
Martin Strauss, Jouni Paulus, Matteo Torcoli, Bernd Edler

Figure 1 for A Hands-on Comparison of DNNs for Dialog SeparationUsing Transfer Learning from Music Source Separation
Figure 2 for A Hands-on Comparison of DNNs for Dialog SeparationUsing Transfer Learning from Music Source Separation
Viaarxiv icon

A Flow-Based Neural Network for Time Domain Speech Enhancement

Jun 16, 2021
Martin Strauss, Bernd Edler

Figure 1 for A Flow-Based Neural Network for Time Domain Speech Enhancement
Figure 2 for A Flow-Based Neural Network for Time Domain Speech Enhancement
Figure 3 for A Flow-Based Neural Network for Time Domain Speech Enhancement
Figure 4 for A Flow-Based Neural Network for Time Domain Speech Enhancement
Viaarxiv icon