Factory Noise Removal to Preserve Situational Awareness

点击翻译按钮获取中文摘要

Abstract According to the CDC NIOSH website “Occupational hearing loss is one of the most common work- related illnesses in the United States.” This is due, in part, to significant numbers of workers exposed to hazardous noise levels in the workplace not using hearing protection devices (HPDs). A National Health and Nutrition Examination Survey estimated that over 20 million U.S. workers are exposed to hazardous noise lev- els at work annually, and one-third of those workers reported non-use of HPDs. In the construction industry, half report being exposed to hazardous noise levels but, of those, one-third report not wearing any HPDs and one quarter have a hearing impairment. Likewise, in manufacturing, about half report exposure to hazardous noise levels, but one quarter don’t wear protection and 20% have a hearing impairment. Our experience is that the non-use of HPDs on factory floors is often not due to the cost of such devices or lack of availability. In many cases, ear plugs and other HPDs can be seen hanging around a worker’s neck or stuffed in a pocket! The problem is that, in addition to blocking hazardous sounds, HPDs also block all other sounds in the environ- ment. This is important because awareness of alarms (e.g., assembly line jams, backing forklifts, and moving cranes) is critical for physical safety and job performance in these industries. We propose a novel hearing protection system that provides enhanced access to “situational” sounds such as alarms, forklifts and voices, while suppressing hazardously loud noises. By overcoming the environmental-awareness obstacle, we believe workers will be more willing to wear our HPD. Our solution uses innovative and patented signal pro- cessing technologies to “scrub” hazardously loud sounds, each of which has been “tagged” by an adjacent microphone, from the response mixtures of other “environmental” microphones placed in more acoustically diverse locations in the workspace. This scrubbing process removes the tagged noises from the response sig- nals of the environmental microphones, thereby enhancing the audibility of the other important sounds in the environment. The envisioned commercial product will perform such scrubbing and then present the remaining situational sounds in a worker’s ear using existing acoustically isolating headphones. In the Phase I project, we propose to construct, validate, and scrub a sequence of increasingly complex audio mixtures made up of typi- cal loud machinery sounds plus softer situational sounds. Our ability to scrub the loud noises from those mix- tures will be objectively measured. In Aim 1, the mixtures are constructed from pairs of recorded noise and situational sound. In Aim 2, we will record and analyze sound pairs generated in a machine shop. In Aim 3, we will “push the envelope”, both by increasing the number and complexity of noise and signal components in the mixtures and by moving situational sources and changing room acoustics. Our metric of success is the improvement in the broadband signal to interference ratio (SIR) of the scrubbed mixtures and a characteriza- tion of the environments in which this scrubbing can produce greatly enhanced situational awareness.