Timezone: »

Data-driven Estimation of Sinusoid Frequencies
Gautier Izacard · Sreyas Mohan · Carlos Fernandez-Granda

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #110

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 that 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.

Author Information

Gautier Izacard (Ecole Normale Supérieure)
Sreyas Mohan (NYU)
Carlos Fernandez-Granda (NYU)