Enabling Automatic Disordered Speech Recognition: An Impaired Speech Dataset in the Akan Language
It addresses the problem of developing inclusive speech technologies for low-resource languages like Akan, but it is incremental as it primarily provides a new dataset without novel methods.
This study tackled the lack of impaired speech data in low-resource languages by creating a curated corpus of 50.01 hours of audio recordings from native Akan speakers with speech impairments, including stammering, cerebral palsy, cleft palate, and stroke-induced disorders.
The lack of impaired speech data hinders advancements in the development of inclusive speech technologies, particularly in low-resource languages such as Akan. To address this gap, this study presents a curated corpus of speech samples from native Akan speakers with speech impairment. The dataset comprises of 50.01 hours of audio recordings cutting across four classes of impaired speech namely stammering, cerebral palsy, cleft palate, and stroke induced speech disorder. Recordings were done in controlled supervised environments were participants described pre-selected images in their own words. The resulting dataset is a collection of audio recordings, transcriptions, and associated metadata on speaker demographics, class of impairment, recording environment and device. The dataset is intended to support research in low-resource automatic disordered speech recognition systems and assistive speech technology.