In this paper, we present our radio frequency signal denoising approach, RFDEMUCS, for the 2024 IEEE ICASSP RF Signal Separation Challenge. Our approach is based on the DE-MUCS architecture [1], and has a U-Net structure with a bidirectional LSTM bottleneck. For the task of estimating the underlying bit-sequence message, we also propose an extension of the DEMUCS that directly estimates the bits. Evaluations of the presented methods on the challenge test dataset yield MSE and BER scores of −118.71 and 81, respectively, according to the evaluation metrics defined−in the challenge.
Demucs for Data-Driven RF Signal Denoising / Yapar, Çağkan; Jaensch, Fabian; Hauffen, Jan C.; Pezone, Francesco; Jung, Peter; Dehkordi, Saeid K.; Caire, Giuseppe. - (2024), pp. 95-96. (Intervento presentato al convegno IEEE ICASSP 2024 tenutosi a Seoul; South Korea) [10.1109/ICASSPW62465.2024.10627485].
Demucs for Data-Driven RF Signal Denoising
Francesco Pezone;
2024
Abstract
In this paper, we present our radio frequency signal denoising approach, RFDEMUCS, for the 2024 IEEE ICASSP RF Signal Separation Challenge. Our approach is based on the DE-MUCS architecture [1], and has a U-Net structure with a bidirectional LSTM bottleneck. For the task of estimating the underlying bit-sequence message, we also propose an extension of the DEMUCS that directly estimates the bits. Evaluations of the presented methods on the challenge test dataset yield MSE and BER scores of −118.71 and 81, respectively, according to the evaluation metrics defined−in the challenge.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
