在 ESP32-S3 与 Arduino Nicla Vision 上实现边缘端声音异常持续检测
On-Edge Acoustic Continual Anomaly Detection: A Cross-Platform Comparative Study
工业设备监测不用依赖离线大模型，一块 ESP32-S3 就能跑 82%–95% 的声音异常检测。论文给了 Firebase 加 MQTT 的云端重训练管道设计，做嵌入式或工业物联网的开发者可以直接参考这套边缘持续学习方案。
arXiv 论文（编号 2611.15465）评估了声音异常检测（AAD）在两块嵌入式硬件上的持续学习表现：ESP32-S3（外接 I2S 数字麦克风）与 Arduino Nicla Vision（板载 PDM 麦克风）。
使用 DCASE Challenge Task 2 机器声音数据，通过扬声器重放的受控协议测试。模型采用轻量 ShallowNet 编码器和对比原型学习，将频谱图映射到 32 维嵌入空间。
两块板子运行相同的 TFLM 编码器，在设备端用指数移动平均更新原型；云端通过 Firebase 和 MQTT 管道做远程数据收集与重训练。
结果上 ESP32-S3 在五类机器上达到 82.35%–95.
00% 准确率，Nicla Vision 达到 79.41%–95.
00%，两平台表现接近，说明该轻量原型架构可跨硬件与传感器层级可靠迁移。
On-Edge Acoustic Continual Anomaly Detection: A Cross-Platform Comparative Study
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DCASE, ESP32-S3, TensorFlow Lite Micro, 边缘计算.
Source attribution: curated from arXiv cs.LG (@Rami Zewail, Yehia Ehab, Karim Ali, Ahmed Mahrous, Mohamed Awad, Bassem Mokhtar).