Exploring phoneme representations and their adaptability using fast Auditory Classification Images – fastACI

The fast-ACI project aims to develop a robust experimental method to visualize and characterize the auditory mechanisms involved in phoneme recognition. We will first use this technique to map the phonemic representations used by normal-hearing listeners, a long-standing problem in psycholinguistics. The fast-ACI method relies on a stimulus-response model, fitted using advanced machine learning techniques, to produce an instant picture of a participant’s listening strategy in a given context. As such, it is a powerful tool for exploring the adaptability of speech comprehension in the case of (1) sensorineural hearing loss and (2) noisy backgrounds. Particular attention will be paid to the deleterious interaction between the two factors, an issue of prime importance when seeking to reduce the impact of hearing loss on everyday life. The project will ultimately result in the development of a diagnostic tool, allowing audiologists to objectively measure the listening strategy of their patients and design more individually-tailored solutions.