General framework for signal processing in nonlinear mass-spring networks with application to keyword spotting
Physical Review Applied · 14.10.2025 · 24 (4)
DOI: 10.1103/5hhw-sk9c ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Applied, online erschienen am 14.10.2025. Verfasst von Finn Bohte und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ERC.
Abstract (Originalsprache)
Mechanical systems played a foundational role in computing history, and have regained interest due to their unique properties, such as low damping and the ability to process mechanical signals without transduction. However, recent efforts have focused primarily on elementary computations, implemented in systems based on predefined reservoirs, or in periodic systems such as arrays of buckling beams. Here we numerically demonstrate a passive mechanical system—in the form of a nonlinear mass-spring model—that tackles a real-world benchmark for keyword spotting in speech signals. The model is organized in a hierarchical architecture combining feature extraction and continuous-time convolution, with each individual stage tailored to the physics of the mass-spring systems considered. For each step in the computation, a subsystem is designed by combining a small set of low-order polynomial potentials. These potentials act as fundamental components that interconnect a network of masses. In analogy to electronic circuit design, where complex functional circuits are constructed by combining basic components into hierarchical designs, we refer to this framework as “springtronics.” We introduce springtronic systems with hundreds of degrees of freedom, achieving speech classification accuracy comparable to that of existing submilliwatt electronic systems.
Förderung
- ERC
Zitieren
APA
Bohte, F., Louvet, A., Maillou, V., & Serra-Garcia, M. (2025). General framework for signal processing in nonlinear mass-spring networks with application to keyword spotting. Physical Review Applied, 24(4). https://doi.org/10.1103/5hhw-sk9c
Vancouver
Bohte F, Louvet A, Maillou V, Serra-Garcia M. General framework for signal processing in nonlinear mass-spring networks with application to keyword spotting. Physical Review Applied. 2025;24(4). doi:10.1103/5hhw-sk9c
BibTeX
@article{Bohte2025,
author = {Bohte, Finn and Louvet, Alice and Maillou, Vincent and Serra-Garcia, Marc},
title = {General framework for signal processing in nonlinear mass-spring networks with application to keyword spotting},
journal = {Physical Review Applied},
year = {2025},
volume = {24},
number = {4},
doi = {10.1103/5hhw-sk9c}
}
EUVIMED