RAPID: Human Sound Localization and Analytics

COVID-19正以前所未有的速度传播，导致全球众多人死亡。社交距离是迄今为止限制其传播的最有效方法。然而，手动执行社交距离不仅是劳动密集型的，而且由于可能的身体接触而容易出错甚至是危险的。本项目拟开发技术和移动的系统，定位人类声音，如咳嗽和语音，并警告用户时，有人在社会距离。 如果成功，这项工作将大大推进无线传感和定位的最新技术。为了最大限度地发挥影响，研究人员将与行业和当地社区合作，并向公众发布软件。研究成果也将纳入研究生和本科生课程。拟议的研究旨在开发算法和系统，以定位不受控制和未知的人类声音。一个独特的优势是，它不需要其他手机的合作，无论谁使用它都可以立即受益。它利用手机的移动性，随着用户的移动，以实现本地化。将对低频语音信号进行多分辨率分析，以进一步提高准确性。当另一部手机合作时，它将进一步利用两部手机之间的飞行时间来提高性能。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

COVID-19 is spreading at an unprecedented rate resulting in the death of so many people all over the world. Social distancing is so far the most effective method to limit its spread. However, manually enforcing social distancing is not only labor-intensive but also error-prone and even dangerous due to possible physical contact. This project proposes to develop techniques and mobile systems that localize human sound such as cough and voice and alarm a user when someone is within the social distance. If successful, this work will significantly advance the state-of-the-art in wireless sensing and localization. To maximize the impact, the researchers will collaborate with industry and local community and release software to the public. The research outcome will also be incorporated into the graduate and undergraduate curriculum. The proposed research aims to develop algorithms and systems to localize uncontrolled and unknown human sound. A unique advantage is that it does not require cooperation from other phones and whoever uses it can immediately benefit from it. It exploits the phone mobility as the user moves to enable localization. The multi-resolution analysis will be performed on low-frequency voice signals to further enhance accuracy. When another phone is cooperating, it will further leverage the time of flight between the two phones to improve the performance.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.