Language impairment (LI) in children is pervasive in all walks of life. Automatic prediction of LI is useful as a first pass for speech language pathologists in identifying prospective children with LI. Previous work in the automatic prediction of LI has explored various features, mostly shallow and surface level features. In this paper, we evaluate deeper NLP features such as syntactic, semantic and entity grid model features, along with narrative structure and quality features in the prediction of language impairment using child language transcripts. Our experiments show that narrative structure and quality features along with a combination of other features are helpful in the prediction of language impairment in storytelling narratives. Tue.SS5.11 16:00.18:00 Quantitative Analysis of Pitch in Speech of Children with Neurodevelopmental Disorders Geza Kiss, Jan P.H. van Santen, Emily Tucker Prudfhommeaux, Lois M. Black We analyzed the prosody of children with Autism Spectrum Disorders, Developmental Language Disorders, and Typical Development in conversational speech, using the CSLU ADOS speech corpus. We found several significant differences in the pitch characteristics of these diagnostic groups, and report automatic classification utilizing these features that are significantly better than chance. We show that the choice of pitch tracker, its parameters, and the potential pitch correction can substantially affect the results, thus the scientific relevance of work on prosody.
Index Terms: language impairment, machine learning, natural language processing
Bibliographic reference. Hassanali, Khairun-nisa / Liu, Yang / Solorio, Thamar (2012): "Evaluating NLP features for automatic prediction of language impairment using child speech transcripts", In INTERSPEECH-2012, 1339-1342.