Listener Performance Modeling in Urban Environments

ABSTRACT: The goal of this Small Business Innovative Research project is to predict the ability of human listeners to detect and identify specific auditory targets within complex, real-world sound environments. Previous approaches, based on linear auditory models, have produced mixed results. Our novel approach simulates the nonlinear signal processing observed in auditory physiology, significantly extending the state of the art. By mimicking functionally important nonlinearities, we expect this technology to simulate human perceptual capabilities that are relevant to predicting the detection and identification of auditory targets. During Phase I, we plan to 1) create an explanation for auditory detection and identification based on a nonlinear model of spectral and temporal processing in the human auditory system, 2) build a computer model to produce predictions that can be compared with human data, and 3) test the model against an existing set of human data and design a new experiment for Phase II. A detailed report will be delivered along with a plan for simulating human detection and identification of aircraft by the end of Phase II. The success of the model will inform fundamental scientific research by further elucidating the role of nonlinear processing in the auditory system. BENEFIT: The model of auditory detection and identification we plan to develop for this Phase I project will have broad implications for military, aerospace and automotive technologies. The model will predict sound source detection and identification in military environments, and will provide predictions across a wide variety of background noise configurations. The model may prove useful in military training simulators, which have traditionally relied primarily on visual information and cues. In addition, the development and fielding of an auditory detection model has implications for automotive technology areas, the FAA, the U.S. Department of the Interior and National Park Service, by providing the ability to accurately predict auditory detection of aircraft and automobiles across a wide variety of locations, including residential areas, parks, and commercial zones. More generally, a technology that can successfully recognize complex sound patterns in natural environments would have significant implications for almost every application, military and civilian, that processes sound. Existing systems would be improved, deployment in new environments would be enabled, and new applications would become possible. Military applications would include audio surveillance, biometric security, and sonar. Civilian applications would include hearing technologies, speech technologies, and music applications. Hearing impairment alone is expected to affect 700 million people worldwide by 2015 and such technology would greatly benefit the users of hearing devices. Improvements to speech technologies would include better recognition rates and noise tolerance for speech recognition systems, and improved cell phone clarity in a range of environments. Music applications would be able to automatically segregate polyphonic recordings, yielding new and improved tools for several million musicians, for hundreds of millions of music consumers who enjoy music recommendation systems, and for copyright identification and management systems.