Improving Automatic Recognition of Aphasic Speech with AphasiaBank

Automatic recognition of aphasic speech is challenging due to various speech-language impairments associated with aphasia as well as a scarcity of training data appropriate for this speaker population. AphasiaBank, a shared database of multimedia interactions primarily used by clinicians to study aphasia, offers a promising source of data for Deep Neural Network acoustic modeling. In this paper, we establish the first large-vocabulary continuous speech recognition baseline on AphasiaBank and study recognition accuracy as a function of diagnoses. We investigate several out-of-domain adaptation methods and show that AphasiaBank data can be leveraged to significantly improve the recognition rate on a smaller aphasic speech corpus. This work helps broaden the understanding of aphasic speech recognition, demonstrates the potential of AphasiaBank, and guides researchers who wish to use this database for their own work.