Concept and implementation of an adaptive digital hearing training system for cochlear implant aftercare

Abstract

Within the context of an interdisciplinary research project, we created acutting-edge prototype of an adaptive digital auditory training system designed for cochlear implant (CI) users. By leveraging the evidence-centered design (ECD) framework, we integrated adynamic difficulty adjustment feature that tailors the experience to the unique performance capabilities of each individual user. The ECD provides aconceptual design framework suitable for complex assessments of competence and dynamic performance. In the first phase, the domain of hearing was first defined in the context of CI users. In the development phase the three core models of the ECD, the competence model, the evidence model, and the task model, were developed and implemented. In addition, an asset pool of sound and language files was created, which included comprehensive linguistic feature descriptions for calculating item difficulties. Based on the requirements described, an adaptive exercise generator, an AI service, and other components were implemented. This included the development of agame environment and adashboard for patient data management. The exercises' difficulty levels were determined based on various parameters (e.g., sound, word frequency and number of words, grammatical properties) in combination with defined task types and levels. An adaptive digital auditory training system can help to supervise and train CI patients in acontinuous, interactive process based on their individual needs. We see the ECD as an effective way to build auser-based adaptive system.