Speech and Language Disorders: A systematic review of corpora and future directions

Speech and Language Disorders (SLDs) significantly impact social interaction, communication, and educational outcomes, making them a global health priority. According to data published by Komodo Health, speech disorder diagnoses among children aged 0–12 increased by 110% in 2022, reaching 1.2 million cases compared to the pre-pandemic average of 570,000. Addressing this growing challenge requires empowering the research community with diverse and comprehensive corpora to drive investigations and develop innovative tools. This paper systematically reviews existing SLD corpora, evaluating their relevance to research and technological innovation. The corpora are categorized based on target population, language, data modality, and task domain. Thirteen SLDs are explored, including neurological language breakdown, motor speech disorders, child language impairments, and communication challenges in autism spectrum disorder. The review identifies key research directions in the field of SLD and highlights critical gaps and challenges using statistical insights drawn from the analysed search. Emerging trends such as multimodal data integration and artificial intelligence applications for advanced data analysis are emphasised. The review concludes with recommendations for enhancing the utility and accessibility of SLD corpora, underscoring the importance of interdisciplinary collaboration and community engagement to address existing limitations. This review serves as a valuable resource for clinicians and researchers, guiding them in selecting the most suitable database/corpora to address their clinical and investigative needs while advancing the field of SLD research and innovation. • The paper systematically reviews available databases for speech and language disorders. • The review identifies gaps in existing databases, including underrepresented speech and language disorders. • It categorizes databases by disorder type, data modality, and intended research use. • The study emphasizes the need for interdisciplinary collaboration in research. • The paper provides a roadmap for improving data collection and future research initiatives.