Bioinspired recognition of cricket calling songs in sub-nanowatt inter-pulse delay detector
Source abstract
Abstract
Abstract Energy efficiency is one of the main concerns in the design of embedded circuits, especially considering the ever-growing amount of portable devices produced for specialized to everyday life applications. Taking inspiration from neuronal processes in the brain, neuromorphic systems are seen as promising solutions to this concern. Great advances in all fields led to the production of numerous hardware implementations, digital or mixed-signal for the most part. While digital systems showcase high accuracy performances and an advanced technological maturity, they fail to reach the ultra-low power (ULP) consumptions of emerging technologies or fully analog implementations due to generally non-dedicated chips and bulky hardware. In this work, we designed and implemented a bioinspired analog demonstrator of inter-pulse delay detection on standard complementary metal oxide semiconductor in the subthreshold operation mode. Relying on the temporal pattern recognition mechanism in female field crickets, our circuit reach on average 750 pW of total power consumption under probes during detection on real-world recordings of male crickets calling song. The circuit was evaluated in quiet, noisy, and multi-source environments, demonstrating strong detection performances given its sparse architecture and ULP consumption.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Semiconductor Quantum Structures and Devices · Advanced Memory and Neural Computing · Neural Networks and Reservoir Computing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. The evolution of rhythm processing10.1016/j.tics.2018.08.002 ↗
2. Data augmentation and deep learning methods in sound classification: a systematic review10.3390/electronics11223795 ↗
3. Benchmarking neuromorphic hardware and its energy expenditure10.3389/fnins.2022.873935 ↗
4. Roadmap to neuromorphic computing with emerging technologies10.1063/5.0179424 ↗
5. Spatiotemporal audio feature extraction with dynamic memristor-based time-surface neurons10.1126/sciadv.adl2767 ↗
6. A lightweight convolutional spiking neural network for fires detection based on acoustics10.3390/electronics13152948 ↗
7. Auditory anomaly detection using recurrent spiking neural networks10.1109/AICAS59952.2024.10595878 ↗
8. Enhanced multiple sound event detection and classification using physical signal properties in recurrent spiking neural networks10.1109/ACCESS.2025.3563346 ↗
9. Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection10.1109/ICASSP40776.2020.9053412 ↗
10. A bin encoding training of a spiking neural network based voice activity detection10.1109/ICASSP40776.2020.9054761 ↗
11. Deep spiking neural networks for large vocabulary automatic speech recognition10.3389/fnins.2020.00199 ↗
12. Using a low-power spiking continuous time neuron (SCTN) for sound signal processing10.3390/s21041065 ↗
13. A 71.2-μW speech recognition accelerator with recurrent spiking neural network10.1109/TCSI.2024.3387993 ↗
14. Truenorth: design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip10.1109/TCAD.2015.2474396 ↗
15. Loihi: a neuromorphic manycore processor with on-chip learning10.1109/MM.2018.112130359 ↗
16. Benchmarking keyword spotting efficiency on neuromorphic hardware10.1145/3320288.3320304 ↗
17. An auditory feature detection circuit for sound pattern recognition10.1126/sciadv.1500325 ↗
18. Synaptic delays for insect-inspired temporal feature detection in dynamic neuromorphic processors10.3389/fnins.2020.00150 ↗
19. A scalable multicore architecture with heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAPs)10.1109/TBCAS.2017.2759700 ↗
20. Spatiotemporal pattern recognition in single mixed-signal VLSI neurons with heterogeneous dynamic synapses10.1145/3546790.3546794 ↗
21. A 4-fJ/spike artificial neuron in 65 nm CMOS technology10.3389/fnins.2017.00123 ↗
22. Voltage oscillations in the barnacle giant muscle fiber10.1016/S0006-3495(81)84782-0 ↗
23. Sequential filtering processes shape feature detection in crickets: a framework for song pattern recognition10.3389/fphys.2016.00046 ↗
24. Xeno-canto:: sharing bird sounds from around the world
25. A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses10.3389/fnins.2015.00141 ↗
26. Synaptic dynamics in analog VLSI10.1162/neco.2007.19.10.2581 ↗
27. Neuromorphic coincidence detector for interaural time difference encoding and sound DOA estimation10.1109/TIM.2024.3460950 ↗