Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices
This work addresses the challenge of enabling advanced sound classification on low-power edge devices, which is incremental as it builds on existing compression techniques but applies them in a novel pipeline for acoustic networks.
The paper tackles the problem of deploying deep acoustic networks on extremely resource-constrained edge devices by presenting a generic pipeline that compresses and quantizes large networks, achieving state-of-the-art accuracy on multiple datasets (e.g., 96.65% on ESC-10) and reducing model size by 97.22% and FLOPs by 97.28% while maintaining close to state-of-the-art performance.
Significant efforts are being invested to bring state-of-the-art classification and recognition to edge devices with extreme resource constraints (memory, speed, and lack of GPU support). Here, we demonstrate the first deep network for acoustic recognition that is small, flexible and compression-friendly yet achieves state-of-the-art performance for raw audio classification. Rather than handcrafting a once-off solution, we present a generic pipeline that automatically converts a large deep convolutional network via compression and quantization into a network for resource-impoverished edge devices. After introducing ACDNet, which produces above state-of-the-art accuracy on ESC-10 (96.65%), ESC-50 (87.10%), UrbanSound8K (84.45%) and AudioEvent (92.57%), we describe the compression pipeline and show that it allows us to achieve 97.22% size reduction and 97.28% FLOP reduction while maintaining close to state-of-the-art accuracy 96.25%, 83.65%, 78.27% and 89.69% on these datasets. We describe a successful implementation on a standard off-the-shelf microcontroller and, beyond laboratory benchmarks, report successful tests on real-world datasets.