Atypical Prosodic Structure as an Indicator of Reading Level and Text Difficulty

Automatic assessment of reading ability builds on applying speech recognition tools to oral reading, measuring words correct per minute. This work looks at more fine-grained analysis that accounts for effects of prosodic context using a large corpus of read speech from a literacy study. Experiments show that lower-level readers tend to produce relatively more lengthening on words that are not likely to be final in a prosodic phrase, i.e. in less appropriate locations. The results have implications for automatic assessment of text difficulty in that locations of atypical prosodic lengthening are indicative of difficult lexical items and syntactic constructions.