Data-driven Estimation of Sinusoid Frequencies [article]

Gautier Izacard, Sreyas Mohan, Carlos Fernandez-Granda
2021 arXiv   pre-print
Frequency estimation is a fundamental problem in signal processing, with applications in radar imaging, underwater acoustics, seismic imaging, and spectroscopy. The goal is to estimate the frequency of each component in a multisinusoidal signal from a finite number of noisy samples. A recent machine-learning approach uses a neural network to output a learned representation with local maxima at the position of the frequency estimates. In this work, we propose a novel neural-network architecture
more » ... hat produces a significantly more accurate representation, and combine it with an additional neural-network module trained to detect the number of frequencies. This yields a fast, fully-automatic method for frequency estimation that achieves state-of-the-art results. In particular, it outperforms existing techniques by a substantial margin at medium-to-high noise levels.
arXiv:1906.00823v3 fatcat:sy6fgytqgjcdrnyd2o3kiloije