Automatic Scoring of Children's Read-Aloud Text Passages and Word Lists

Assessment of reading proficiency is typically done by asking subjects to read a text passage silently and then answer questions related to the text. An alternate approach, measuring reading-aloud proficiency, has been shown to correlate well with the aforementioned common method and is used as a paradigm in this paper. We describe a system that is able to automatically score two types of children’s read speech samples (text passages and word lists), using automatic speech recognition and the target criterion “correctly read words per minute”. Its performance is dependent on the data type (passages vs. word lists) as well as on the relative difficulty of passages or words for individual readers. Pearson correlations with human assigned scores are around 0.86 for passages and around 0.80 for word lists.