A new automated vocal analysis technology can discriminate pre-verbal vocalizations of very young children with autism with 86% accuracy. The LENA™ (Language Environment Analysis) system also differentiated typically developing children and children with autism from children with language delay. The processor fits into the pocket of specially designed children's clothing and records everything the child vocalizes. LENA could not only enable better early diagnosis of autism spectrum disorders, but also allow parents to continue and supplement language enrichment therapy at home and assess their own effectiveness for themselves.