Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Pronunciation Verification of Childrenís Speech for Automatic Literacy Assessment

Joseph Tepperman (1), Jorge Silva (1), Abe Kazemzadeh (1), Hong You (2), Sungbok Lee (1), Abeer Alwan (2), Shrikanth Narayanan (1)

(1) University of Southern California, USA; (2) University of California at Los Angeles, USA

Arguably the most important part of automatically assessing a new readerís literacy is in verifying his pronunciation of read-aloud target words. But the pronunciation evaluation task is especially difficult in children, non-native speakers, and pre-literates. Traditional likelihood ratio thresholding methods do not generalize easily, and even expert human evaluators do not always agree on what constitutes an acceptable pronunciation. We propose new recognition- and alignment-based features in a decision tree classification framework, along with the use of prior linguistic information and human perceptual evaluations. Our classification methods demonstrate a 91% agreement with the voted results of 20 human evaluators who agree among themselves 85% of the time.

Full Paper

Bibliographic reference.  Tepperman, Joseph / Silva, Jorge / Kazemzadeh, Abe / You, Hong / Lee, Sungbok / Alwan, Abeer / Narayanan, Shrikanth (2006): "Pronunciation verification of children≤s speech for automatic literacy assessment", In INTERSPEECH-2006, paper 1814-Tue1WeS.8.