Practical Considerations for Acoustic Source Localization in the IoT Era: Platforms, Energy Efficiency, and Performance

Abstract

The rapid development of the Internet of Things (IoT) has posed important changes in the way emerging acoustic signal processing applications are conceived. While traditional acoustic processing applications have been developed taking into account high-throughput computing platforms equipped with expensive multichannel audio interfaces, the IoT paradigm is demanding the use of more flexible and energy-efficient systems. In this context, algorithms for source localization and ranging in wireless acoustic sensor networks can be considered an enabling technology for many IoT-based environments including security, industrial and health-care applications. This paper is aimed at evaluating important aspects dealing with the practical deployment of IoT systems for acoustic source localization. Recent Systems-On-Chip (SoC) composed of low-power multicore processors, combined with a small graphics accelerator (or GPU), yield a notable increment of the computational capacity needed in intensive signal processing algorithms while partially retaining the appealing low power consumption of embedded systems. Different algorithms and implementations over several state-of-the-art platforms are discussed, analyzing important aspects such as the trade-offs between performance, energy efficiency and exploitation of parallelism by taking into account real-time constraints.

Short-Range Audio Channels Security: Survey of Mechanisms, Applications, and Research Challenges

“…While the solutions discussed above will be further discussed throughout the paper, many other techniques to achieve source localization using acoustic signals are available. We refer the interested readers to the contributions already available in the literature, surveying methods for acoustic source localization [1], [43], [44].…”

“…S Ound, including human speech, is commonly considered as a natural and intuitive means to quickly interact with automatic devices [1]. Indeed, ambient sounds, as well as voice commands issued towards audio-enabled devices, are often conceived as a natural, intuitive, and minimal effort approach for humans to communicate with machines, especially if compared to human-imperceptible Radio Frequency (RF) transmissions and distracting visual-tactile interfaces [2].…”

The Internet of Audio Things: State of the Art, Vision, and Challenges

“…Most large scale WASNs do not consider the acoustic relations between the audio content captured at different nodes, which for instance, can be exploited for source localization. Nevertheless, for smaller scale WASNs, or for more advanced nodes, source localization (single or multiple) can be performed using various techniques and algorithms (see, e.g., [75], [76], [77], [78], [79], [80], [81]).…”

Computation of Psycho-Acoustic Annoyance Using Deep Neural Networks

“…A more extensive study on the calculation of psycho-acoustic parameters in a WASN using Raspberry Pi is provided in [19]. Although more powerful platforms could be used for this purpose, the deployment cost would also increase significantly [20]. Thus, these results motivate the proposal of a different computational approach capable of predicting faster PA values.…”