3 papers
eess.AS2023
EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement
Marvin Sach, Jan Franzen, Bruno Defraene +4
Fully convolutional recurrent neural networks (FCRNs) have shown state-of-the-art performance in single-channel speech enhancement. However, the number of parameters and the FLOPs/…
eess.AS2021
AEC in a NetShell: On Target and Topology Choices for FCRN Acoustic Echo Cancellation
Jan Franzen, Ernst Seidel, Tim Fingscheidt
Acoustic echo cancellation (AEC) algorithms have a long-term steady role in signal processing, with approaches improving the performance of applications such as automotive hands-fr…
eess.AS2021
Y-Net FCRN for Acoustic Echo and Noise Suppression
Ernst Seidel, Jan Franzen, Maximilian Strake +1
In recent years, deep neural networks (DNNs) were studied as an alternative to traditional acoustic echo cancellation (AEC) algorithms. The proposed models achieved remarkable perf…