RFSS: A Multi-Standard RF Signal Source Separation Dataset with 3GPP-Standardized Channel and Hardware Impairments

TL;DR

This paper introduces RFSS, a comprehensive open-source dataset of 100,000 multi-standard RF signals with realistic impairments, enabling data-driven research on source separation for 2G-5G coexistence.

Contribution

The creation of RFSS, the first large-scale, multi-standard RF dataset with standardized channel and hardware impairments, and benchmarking of separation methods on this dataset.

Findings

Conv-TasNet outperforms ICA by 13.7 dB in PI-SI-SINR on 2-source mixtures.

The dataset includes GSM, UMTS, LTE, and 5G NR signals with realistic impairments.

Benchmark results highlight the challenges and progress in RF source separation.

Abstract

The coexistence of heterogeneous cellular standards (2G-5G) in shared spectrum demands sophisticated RF source separation techniques, yet no public dataset exists for data-driven research on this problem. We present RFSS (RF Signal Source Separation), an open-source dataset of 100,000 multi-source RF signal samples generated with full 3GPP standards compliance. The dataset covers GSM (TS 45.004), UMTS (TS 25.211), LTE (TS 36.211), and 5G NR (TS 38.211), with 2-4 simultaneous sources per sample plus 4,000 single-source reference samples, at 30.72 MHz sample rate. Each sample passes through independent 3GPP TDL multipath fading channels and realistic hardware impairments: carrier frequency offset, I/Q imbalance, phase noise, DC offset, and PA nonlinearity (Rapp model). Two mixing modes are provided: co-channel (all sources at baseband) and adjacent-channel (each source frequency-shifted to its standard-specific carrier). The dataset totals 103 GB in HDF5 format with a 70/15/15 train/validation/test split. We benchmark five methods: FastICA, Frobenius-norm NMF, Conv-TasNet, DPRNN, and a CNN-LSTM baseline, evaluated using permutation-invariant SI-SINR (PI-SI-SINR). Conv-TasNet achieves -21.18 dB PI-SI-SINR on 2-source mixtures versus -34.91 dB for ICA, a 13.7 dB improvement. On co-channel mixtures, Conv-TasNet reaches -12.34 dB versus -28.04 dB for ICA and -16.19 dB for NMF. The dataset and evaluation code are publicly released at submission time.