Nicholas A. Lesica

This paper develops a deep learning-based hearing aid that restores neural coding by simulating normal auditory processing in impaired brains, outperforming existing methods in distortion correction and phoneme recognition.

The paper introduces ICNet, a deep learning model that accurately simulates neural dynamics in the auditory midbrain across various sounds, including speech.

The paper analyzes neural responses to complex music, finding a tradeoff between reliability and dimensionality in the neural code as musical complexity increases.

The paper investigates how hearing loss distorts neural signal dynamics, leading to hypersensitivity to background noise, using brain recordings and deep neural networks.

This study investigates how hearing loss affects neural encoding of speech, finding that temporal masking and rollover phenomena impact speech discrimination in both normal and hearing-impaired animals.