Enabling Automatic Disordered Speech Recognition: An Impaired Speech Dataset in the Akan Language

TL;DR

This paper introduces a new dataset of 50 hours of impaired speech in the Akan language, enabling research in automatic disordered speech recognition for low-resource languages.

Contribution

It provides the first curated corpus of impaired speech in Akan, including diverse impairment types, to facilitate development of inclusive speech recognition technologies.

Findings

Dataset includes 50.01 hours of speech data across four impairment types.

Includes transcriptions and metadata for comprehensive analysis.

Supports research in low-resource disordered speech recognition.

Abstract

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.