loading page

Grid-free Harmonic Retrieval and Model Order Selection using Convolutional Neural Networks
  • +3
  • Steffen Schieler,
  • Sebastian Semper,
  • Reza Faramarzahangari,
  • Michael Döbereiner,
  • Christian Schneider,
  • Reiner Thomä
Steffen Schieler
Technische Universität Ilmenau, FG EMS

Corresponding Author:[email protected]

Author Profile
Sebastian Semper
Technische Universität Ilmenau, FG EMS
Reza Faramarzahangari
Technische Universität Ilmenau, FG EMS
Michael Döbereiner
Fraunhofer Institute of Integrated Circuits: Dep. EMS
Christian Schneider
Fraunhofer Institute of Integrated Circuits: Dep. EMS
Reiner Thomä
Technische Universität Ilmenau, FG EMS


Harmonic retrieval techniques are the foundation of radio channel sounding, estimation and modeling. This paper introduces a Deep Learning approach for joint delay-and Doppler estimation from frequency and time samples of a radio channel transfer function. Our work estimates the two-dimensional parameters from a signal containing an unknown number of paths. Compared to existing deep learning-based methods, the signal parameters are not estimated via classification but in a quasi-grid-free manner. This alleviates the bias, spectral leakage, and ghost targets that grid-based approaches produce. The proposed architecture also reliably estimates the number of paths in the measurement. Hence, it jointly solves the model order selection and parameter estimation task. Additionally, we propose a multi-channel windowing of the data to increase the estimator's robustness. We also compare the performance to other harmonic retrieval methods and integrate it into an existing maximum likelihood estimator for efficient initialization of a gradient-based iteration.
15 Jan 2024Submitted to TechRxiv
26 Jan 2024Published in TechRxiv