A Novel Vocal Database for Children with Autism Spectrum Disorder: Design, Collection, and Future Applications

Abstract

Autism spectrum disorder (ASD) is one of the most complex neurological disorders, presenting significant challenges in terms of detection, particularly in the early stages. There are numerous theories regarding the methods of detection and the types of data used. Recent research has emerged investigating the potential for distinctive vocal characteristics to manifest in the voices of autistic children in comparison to those of normal children. In order to explore this research domain in greater depth, a voice database has been compiled, comprising recordings of autistic and typically developing children. This database includes 600 recordings from children, aged between 4 and 14 years of both sexes. The samples were diverse in terms of dialect and autism severity. The audio samples were subjected to a process of purification and filtration with the objective of ensuring optimal sound quality. The resulting database is balanced, diverse, and ready for use in future research and studies focused on ASD and phonetics.

Keywords

• Autism Spectrum Disorder(ASD)
• Data collection
• Audio dataset
• Arabic speech analysis

References

1. Catherine Lord, Mayada Elsabbagh, Gillian Baird, and Jeremy Veenstra VanderWeele. Autism spectrum disorder. The Lancet, 392(10146):508–520, 2018.
2. Eric P. Hazen, Jessica L. Stornelli, Julia A. O’Rourke, Kathryn Koesterer, and Christopher J. McDougle. Sensory symptoms in autism spectrum disorders. Harvard Review of Psychiatry, 22(2):112–124, 2014.
3. Tomoya Hirota and Bryan H. King. Autism spectrum disorder: a review. JAMA, 329(2):157–168, 2023.
4. Hiroki Ohashi and David J. Ostry. Neural development of speech sensorimotor learning. Journal of Neuroscience, 41(18):4023–4035, 2021.
5. Heather MacFarlane, Ahmed C. Salem, Liabo Chen, Meysam Asgari, and Eric Fombonne. Combining voice and language features improves automated autism detection. Autism Research, 15(7):1288–1300, 2022.
6. Manuel Milling, Alice Baird, Kathrin D. Bartl-Pokorny, S. Liu, A. M. Alcorn, J. Shen, T. Tavassoli, E. Ainger, E. Pellicano, M. Pantic, et al. Evaluating the impact of voice activity detection on speech emotion recognition for autistic children. Frontiers in Computer Science, 4:837269, 2022.
7. MeysamAsgari, Liabo Chen, and Eric Fombonne. Quantifying voice characteristics for detecting autism. Frontiers in Psychology, 12:665096, 2021.
8. A. Mohanta, P. Mukherjee, and V. K. Mirtal. Acoustic features characterization of autism speech for automated detection and classification. In 2020 National Conference on Communications (NCC), pages 1–6. IEEE, 2020.

9. S. Lee, J. Mun, S. Kim, and M. Chung. Speech corpus for Korean children with autism spectrum disorder: towards automatic assessment systems. arXiv preprint arXiv:2402.15539, 2024.
10. J. Kruyt, R. Sabo, K. Polónyiová, D. Ostatníková, and Š. Beňuš. The Slovak autistic and non-autistic child speech corpus: Task-oriented child-adult interactions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16094 16099, 2024.
11. Davida Fromm and Brian MacWhinney. Clinical corpus linguistics. In The Handbook of Clinical Linguistics, pages 143–156. Second edition edition, 2024.
12. Riccardo Fusaroli, Anna Lambrechts, Dan Bang, Dermot M. Bowler, and Sebastian B. Gaigg. Is voice a marker for autism spectrum disorder? A systematic review and meta-analysis. Autism Research, 10(3):384–407, 2017.
13. J. Strunk, M. Leisen, and C. Schubert. Using a multidisciplinary approach with children diagnosed with autism spectrum disorder. Journal of Interprofessional Education & Practice, 8:60–68, 2017.
14. M.A.Saleh, F. A. Hanapiah, and H. Hashim. Robot applications for autism: a comprehensive review. Disability and Rehabilitation: Assistive Technology, 16(6):580-602, 2021.