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

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.