Urban sound classifcation using neural networks on embedded FPGAs

Abstract

Sound classifcation using neural networks has recently produced very accurate results. A large number of diferent applications use this type of sound classifers such as controlling and monitoring the type of activity in a city or identifying different types of animals in natural environments. While traditional acoustic processing applications have been developed on high-performance computing platforms equipped with expensive multi-channel audio interfaces, the Internet of Things (IoT) paradigm requires the use of more fexible and energy-efcient systems. Although software-based platforms exist for implementing general-purpose neural networks, they are not optimized for sound classifcation, wasting energy and computational resources. In this work, we have used FPGAs to develop an ad hoc system where only the hardware needed for our application is synthesized, resulting in faster and more energy-efcient circuits. The results show that our developments are accelerated by a factor of 35 compared to a software-based implementation on a Raspberry Pi.