Acoustic Anomaly Detection (AAD) serves as a non-contact approach for machine condition monitoring, yet much of the existing research is evaluated offline and rarely addresses embedded hardware constraints or microphone variations under operational drift. This paper presents a comparative evaluation of on-edge continual AAD across two embedded platforms the ESP32-S3 (with an external I2S digital microphone) and the Arduino Nicla Vision (with an onboard Pulse Density Modulation (PDM) microphone) using a shared detection model. The model utilizes a lightweight ShallowNet encoder and contrastive prototype learning to map spectrograms into a 32-dimensional embedding space. Both boards run an identical TensorFlow Lite for Microcontrollers (TFLM) encoder, performing on-device prototype learning updated via an exponential moving average. A cloud pipeline orchestrated through Firebase and MQTT enables remote data collection and retraining. Evaluated via a controlled speaker-replay protocol using standardized Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge Task 2 machine sounds, the ESP32-S3 achieved 82.35% to 95.00% accuracy across five machine types, while the Nicla Vision achieved 79.41% to 95.00%. The two platforms demonstrated comparable performance, confirming that the lightweight prototypical architecture transfers reliably across distinct hardware and sensor tiers.
Figures & tables
Parameter
Symbol / Identifier
Value
Audio Sample Rate
SAMPLE_RATE
16,000 Hz
FFT Frame Length
FRAME_LEN
480 (30 ms)
FFT Frame Hop
FRAME_STEP
320 (20 ms)
Number of Temporal Frames
NUM_FRAMES
49
FFT Size
FFT_SIZE
512
Frequency Buckets
NUM_BUCKETS
43
TABLE I: Shared System Hyperparameters and Configuration
Fig. 1: Encased Arduino Nicla Vision deployment platform featuring external antenna connectivity and secure acrylic mounting for physical playback evaluation.
Fig. 2: Controlled physical speaker-replay experimental pipeline. Calibrated DCASE benchmark machine recordings are emitted via a reference loudspeaker in a closed room and captured by edge microcontrollers running local TFLM inference.
Machine Type
Benchmark Source Dataset
Normal ( n )
Abnormal ( n )
ToyCar
ToyADMOS2 [ 3 ]
17
17
Toy Train
ToyADMOS2 [ 3 ]
17
17
Fan
MIMII / MIMII-DG [ 1 , 5 ]
17
17
Gearbox
MIMII-DUE / MIMII-DG [ 4 , 5 ]
20
20
Slider
MIMII / MIMII-DG [ 1 , 5 ]
20
20
Total
DCASE Task 2 Suite
91
91
TABLE II: Characteristics of the Evaluated DCASE Machine Datasets
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\unicodex20130.0426 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.
Steven C. Nesbit, Victor M. Vergara, Michael A. Felix +4
Information Sciences, CAI-3, Los Alamos National Laboratory, Los Alamos, USA · Information Sciences (CAI-3), Los Alamos National Laboratory, Los Alamos, NM, USA · AeroVironment Inc., Albuquerque, USA +7
Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.
Amar Almaini, Jakob Folz, Ghadeer Ashour
computer science, Deggendorf Institute of Technology, Deggendorf, Germany · Computer Science and Engineering, University of West Bohemia, Pilsen, Czech Republic · The Applied College, King Abdulaziz University, Jeddah, Saudi Arabia
In standard acoustic anomaly detection (ASD), models are usually trained separately for each machine or domain using explicit metadata. However, in realistic deployments, machine identifiers are incomplete, unreliable, or simply unavailable. Thus, metadata-free machinery ASD asks a single model to monitor mixed machine populations without machine IDs. In this paper, we argue that the main failure mode is not a weak detector family, but representation entanglement. The heterogeneous normal modes overlap in frozen pre-trained feature spaces, making anomaly scoring and approximate retrieval unreliable. We study this problem directly and propose HARMONY (Hierarchical Anchor Retrieval on Manifold for Oblivious-source acoustic aNomalY detection), an anchor-guided geometric repartitioning framework that reorganizes mixed-source features into compact Voronoi regions and reuses this structure for hierarchical retrieval. On DCASE 2020, HARMONY improves mean AUC from 75.40% to 90.00% (14.60 percentage points) over the strongest unified baseline and from 83.90% to 90.00% over a strong foundation-feature baseline. On a single CPU, its hierarchical retrieval achieves a 7.8x speedup over exhaustive search with only a 0.20 percentage-point AUC drop. These results suggest that incorporating explicit geometric partitioning can improve both detection accuracy and retrieval efficiency for ASD. Code is available at https://github.com/Zzyh0208/HARMONY.
Yuhang Zhang, Yang Li, Qiang Wu +1
School of Software and Microelectronics, Peking University, Beijing, China · Independent Researcher · Collaborative Innovation Center for Western Ecological Safety, Lanzhou University, Lanzhou, China +2