Adaptive-Sampling Mamba–Conv-TasNet for Single-Channel Blind Separation of Electromagnetic Signals

In passive electromagnetic detection and positioning systems, the complex electromagnetic environment poses significant theoretical challenges to traditional single-channel blind source separation (SCBSS) algorithms. To address the need to balance separation quality, computational efficiency, resource use and generalisation across different detection conditions, we present the Adaptive-Sampling Mamba–Conv-TasNet, which integrates physically constrained front-end routing with local and long-range sequence modelling. A condition encoder estimates each mixture’s occupied bandwidth and characteristic time scale. It then selects the lowest-rate, anti-aliased profile that preserves the detected band. Four parallel convolutional kernels extract multiscale local features. The separator combines Conv-TasNet-based local modelling with Mamba-based long-range sequence modelling. A shared mask head produces two source-specific masks, and profile-specific decoders subsequently reconstruct two complex-baseband sources. Across three test sets and nine evaluated methods, the proposed model attains the lowest mean complex NMSE on every dataset and the lowest cross-domain log-PSD RMSE while maintaining moderate latency, model size and memory demand. These results indicate that the Adaptive-Sampling Mamba–Conv-TasNet offers a favourable overall trade-off among separation quality, computational efficiency, resource use and cross-domain generalisation relative to the evaluated methods.