A deep neural-network classifier for photograph-based estimation of hearing protection attenuation and fit.

Occupational and recreational acoustic noise exposure is known to cause permanent hearing damage and reduced quality of life, which indicates the importance of noise controls including hearing protection devices (HPDs) in situations where high noise levels exist. While HPDs can provide adequate protection for many noise exposures, it is often a challenge to properly train HPD users and maintain compliance with usage guidelines. HPD fit-testing systems are commercially available to ensure proper attenuation is achieved, but they often require specific facilities designed for hearing testing (e.g., a quiet room or an audiometric booth) or special equipment (e.g., modified HPDs designed specifically for fit testing). In this study, we explored using visual information from a photograph of an HPD inserted into the ear to estimate hearing protector attenuation. Our dataset consists of 960 unique photographs from four types of hearing protectors across 160 individuals. We achieved 73% classification accuracy in predicting if the fit was greater or less than the median measured attenuation (29 dB at 1 kHz) using a deep neural network. Ultimately, the fit-test technique developed in this research could be used for training as well as for automated compliance monitoring in noisy environments to prevent hearing loss.

Speaker separation in realistic noise environments with applications to a cognitively-controlled hearing aid.

Future wearable technology may provide for enhanced communication in noisy environments and for the ability to pick out a single talker of interest in a crowded room simply by the listener shifting their attentional focus. Such a system relies on two components, speaker separation and decoding the listener's attention to acoustic streams in the environment. To address the former, we present a system for joint speaker separation and noise suppression, referred to as the Binaural Enhancement via Attention Masking Network (BEAMNET). The BEAMNET system is an end-to-end neural network architecture based on self-attention. Binaural input waveforms are mapped to a joint embedding space via a learned encoder, and separate multiplicative masking mechanisms are included for noise suppression and speaker separation. Pairs of output binaural waveforms are then synthesized using learned decoders, each capturing a separated speaker while maintaining spatial cues. A key contribution of BEAMNET is that the architecture contains a separation path, an enhancement path, and an autoencoder path. This paper proposes a novel loss function which simultaneously trains these paths, so that disabling the masking mechanisms during inference causes BEAMNET to reconstruct the input speech signals. This allows dynamic control of the level of suppression applied by BEAMNET via a minimum gain level, which is not possible in other state-of-the-art approaches to end-to-end speaker separation. This paper also proposes a perceptually-motivated waveform distance measure. Using objective speech quality metrics, the proposed system is demonstrated to perform well at separating two equal-energy talkers, even in high levels of background noise. Subjective testing shows an improvement in speech intelligibility across a range of noise levels, for signals with artificially added head-related transfer functions and background noise. Finally, when used as part of an auditory attention decoder (AAD) system using existing electroencephalogram (EEG) data, BEAMNET is found to maintain the decoding accuracy achieved with ideal speaker separation, even in severe acoustic conditions. These results suggest that this enhancement system is highly effective at decoding auditory attention in realistic noise environments, and could possibly lead to improved speech perception in a cognitively controlled hearing aid.

Deep Neural Network Model of Hearing-Impaired Speech-in-Noise Perception.

Many individuals struggle to understand speech in listening scenarios that include reverberation and background noise. An individual's ability to understand speech arises from a combination of peripheral auditory function, central auditory function, and general cognitive abilities. The interaction of these factors complicates the prescription of treatment or therapy to improve hearing function. Damage to the auditory periphery can be studied in animals; however, this method alone is not enough to understand the impact of hearing loss on speech perception. Computational auditory models bridge the gap between animal studies and human speech perception. Perturbations to the modeled auditory systems can permit mechanism-based investigations into observed human behavior. In this study, we propose a computational model that accounts for the complex interactions between different hearing damage mechanisms and simulates human speech-in-noise perception. The model performs a digit classification task as a human would, with only acoustic sound pressure as input. Thus, we can use the model's performance as a proxy for human performance. This two-stage model consists of a biophysical cochlear-nerve spike generator followed by a deep neural network (DNN) classifier. We hypothesize that sudden damage to the periphery affects speech perception and that central nervous system adaptation over time may compensate for peripheral hearing damage. Our model achieved human-like performance across signal-to-noise ratios (SNRs) under normal-hearing (NH) cochlear settings, achieving 50% digit recognition accuracy at -20.7 dB SNR. Results were comparable to eight NH participants on the same task who achieved 50% behavioral performance at -22 dB SNR. We also simulated medial olivocochlear reflex (MOCR) and auditory nerve fiber (ANF) loss, which worsened digit-recognition accuracy at lower SNRs compared to higher SNRs. Our simulated performance following ANF loss is consistent with the hypothesis that cochlear synaptopathy impacts communication in background noise more so than in quiet. Following the insult of various cochlear degradations, we implemented extreme and conservative adaptation through the DNN. At the lowest SNRs (<0 dB), both adapted models were unable to fully recover NH performance, even with hundreds of thousands of training samples. This implies a limit on performance recovery following peripheral damage in our human-inspired DNN architecture.