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.

Optimization of pharmacological interventions in the guinea pig animal model-a new approach to calculate the perilymph volume of the scala tympani

Objective

The guinea pig serves as a well-established animal model for inner ear research, offering valuable insights into the anatomy, physiology, and therapeutic interventions of the auditory system. However, the heterogeneity of results observed in both in-vivo experiments and clinical studies poses challenges in understanding and optimizing pharmacotherapy outcomes. This heterogeneity may be due to individual differences in the size of the guinea pig cochlea and thus in the volume of the scala tympani (ST), which can lead to different drug concentrations in the ST, a fact that has been largely overlooked thus far. To address this issue, we aimed to develop an approach for calculating the individual volume of perilymph within the ST before and after cochlear implant insertion.

Method

In this study, high-resolution μCT images of a total of n = 42 guinea pig temporal bones were used to determine the volume of the ST. We compared fresh, frozen, and fixed tissues from both colored and albino strains to evaluate the potential influence of tissue condition and strain on the results.

Results

Our findings demonstrate a variability in mean ST volume with a relative standard deviation (RSD) of 14.7%, comparable to studies conducted with humans (range RSD: 5 to 20%). This indicates that the guinea pig cochlea exhibits similar variability to that of the human cochlea. Consequently, it is crucial to consider this variability when designing and conducting studies utilizing the guinea pig as an animal model. Furthermore, we successfully developed a tool capable of estimating ST volume without the need for manual segmentation, employing two geometric parameters, basal diameter (A) and width (B) of the cochlea, corresponding to the cochlear footprint. The tool is available for free download and use on our website.

Conclusion

This novel approach provides researchers with a valuable tool to calculate individual ST volume in guinea pigs, enabling more precise dosing strategies and optimization of drug concentrations for pharmacotherapy studies. Moreover, our study underscores the importance of acknowledging and accounting for inter-individual variability in animal models to enhance the translational relevance and applicability of research outcomes in the field of inner ear investigations.