Signal-to-noise ratio (SNR) is a priori information necessary for many signal processing\nalgorithms or techniques. However, there are many problems exsisting in conventional SNR estimation\ntechniques, such as limited application range of modulation types, narrow effective estimation range\nof signal-to-noise ratio, and poor ability to accommodate non-zero timing offsets and frequency offsets.\nIn this paper, an SNR estimation technique based on deep learning (DL) is proposed, which is a\nnon-data-aid (NDA) technique. Second and forth moment (M2M4) estimator is used as a benchmark,\nand experimental results show that the performance and robustness of the proposed method are\nbetter, and the applied ranges of modulation types is wider. At the same time, the proposed method\nis not only applicable to the baseband signal and the incoherent signal, but can also estimate the SNR\nof the intermediate frequency signal.
Loading....