Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring

arXiv:2608.18341v1 Announce Type: cross Abstract: Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity. We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 neuromorphic processor under clean and noisy conditions. Log-mel features are computed off chip; normalization, autoencoder inference, L1 reconstruction scoring, and thresholding run on chip. In a clean, microphone-position-invariant ToyADMOS ToyCar benchmark, the on-chip model achieves 0.9959 AUC and 0.9785 standardized pAUC at maximum false-positive rate 0.1. In the DCASE 2026 Task 2 ToyCar noisy benchmark, the model achieves source AUC 0.7990, target AUC 0.6466, and pAUC 0.6426, exceeding reported baseline metrics. Power profiling on a 16-chip Loihi 2 VPX system shows real-time throughput with 0.0406$\unicode{x2013}$0.0426 mJ dynamic energy per sample, two orders of magnitude lower than both a CPU and GPU. These results support neuromorphic acoustic anomaly detection as a practical candidate for low-power, persistent machine monitoring.

Authors:Steven C. Nesbit (1), Victor M. Vergara (2), Michael A. Felix (3), Evan T. Kain (4), Luis R. García Carrillo (4), Gerd J. Kunde (5), Andrew T. Sornborger (1) ((1) Information Sciences, CAI-3, Los Alamos National Laboratory, Los Alamos, USA, (2) AeroVironment Inc., Albuquerque, USA, (3) University of New Mexico COSMIAC Research Center, Albuquerque, USA, (4) Air Force Research Laboratory, Kirtland AFB, USA, (5) Nuclear and Particle Physics and Applications, P-3, Los Alamos National Laboratory, Los Alamos, USA)

Abstract:Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity. We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 neuromorphic processor under clean and noisy conditions. Log-mel features are computed off chip; normalization, autoencoder inference, L1 reconstruction scoring, and thresholding run on chip. In a clean, microphone-position-invariant ToyADMOS ToyCar benchmark, the on-chip model achieves 0.9959 AUC and 0.9785 standardized pAUC at maximum false-positive rate 0.1. In the DCASE 2026 Task 2 ToyCar noisy benchmark, the model achieves source AUC 0.7990, target AUC 0.6466, and pAUC 0.6426, exceeding reported baseline metrics. Power profiling on a 16-chip Loihi 2 VPX system shows real-time throughput with 0.0406$\unicode{x2013}$0.0426 mJ dynamic energy per sample, two orders of magnitude lower than both a CPU and GPU. These results support neuromorphic acoustic anomaly detection as a practical candidate for low-power, persistent machine monitoring.

Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)

arXiv:2608.18341 [cs.NE]

(or arXiv:2608.18341v1 [cs.NE] for this version)

https://doi.org/10.48550/arXiv.2608.18341 arXiv-issued DOI via DataCite (pending registration)

aiqbench analysis

Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring

Related coverage