arXiv:2507.02428 · v1
A Cookbook for Community-driven Data Collection of Impaired Speech in LowResource Languages
摘要
This study presents an approach for collecting speech samples to build Automatic Speech Recognition (ASR) models for impaired speech, particularly, low-resource languages. It aims to democratize ASR technology and data collection by developing a "cookbook" of best practices and training for community-driven data collection and ASR model building. As a proof-of-concept, this study curated the first open-source dataset of impaired speech in Akan: a widely spoken indigenous language in Ghana. The study involved participants from diverse backgrounds with speech impairments. The resulting dataset, along with the cookbook and open-source tools, are publicly available to enable researchers and practitioners to create inclusive ASR technologies tailored to the unique needs of speech impaired individuals. In addition, this study presents the initial results of fine-tuning open-source ASR models to better recognize impaired speech in Akan.
作者备注：This version has been reviewed and accepted for presentation at the InterSpeech 2025 conference to be held in Rotterdam from 17 to 21 August. 5 pages and 3 tables