Incorporating multimodality in a computing system makes computing more accessible to a wide range of users, including those with impairments. This work presents a paradigm of a multimodal multimedia computing system to make informatics accessible to visually-impaired users. The system’s infrastructure determines the suitable applications to be used. The user’s context and user data type are considered in determining the types of applications, media and modalities that are appropriate to use. The system design is pervasive, fault-tolerant and capable of self-adaptation under varying conditions (e.g. missing or defective components). It uses machine learning so that the system would behave in a pre-defined manner given a pre-conceived scenario. Incremental learning is adapted for added machine knowledge acquisition. A simulation of system’s behaviour, using a test case scenario, is presented in this paper. This work is our original contribution to an ongoing research to make informatics more accessible to handicapped users.