Efficient Convolutional Neural Network For Audio Event Detection
This work addresses the need for efficient acoustic event detection in distributed systems like sensor networks and IoT, enabling deployment on resource-constrained edge devices, though it is incremental as it optimizes an existing method.
The paper tackles the problem of high memory and computational demands of audio event detection algorithms for resource-constrained edge devices by applying structural optimizations to a convolutional neural network, resulting in a memory reduction by a factor of over 500, a computational effort reduction by a factor of 2.1, and a performance improvement of 9.2%.
Wireless distributed systems as used in sensor networks, Internet-of-Things and cyber-physical systems, impose high requirements on resource efficiency. Advanced preprocessing and classification of data at the network edge can help to decrease the communication demand and to reduce the amount of data to be processed centrally. In the area of distributed acoustic sensing, the combination of algorithms with a high classification rate and resource-constraint embedded systems is essential. Unfortunately, algorithms for acoustic event detection have a high memory and computational demand and are not suited for execution at the network edge. This paper addresses these aspects by applying structural optimizations to a convolutional neural network for audio event detection to reduce the memory requirement by a factor of more than 500 and the computational effort by a factor of 2.1 while performing 9.2% better.