Speech and Language Technology in Education (SLaTE 2013)

Grenoble, France
August 30-September 1, 2013

Predicting Gradation of L2 English Mispronunciations using Crowdsourced Ratings and Phonological Rules

Hao Wang, Xiaojun Qian, Helen Meng

Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR of China

Pedagogically, CAPT systems can be improved by giving effective feedback based on the severity of pronunciation errors. We obtained perceptual gradation of L2 English mispronunciations through crowdsourcing, and conducted quality control utilizing the WorkerRank algorithm to refine the collected results and reach a reliable consensus on the ratings of word mispronunciations. This paper presents our work on modeling the relationship between the phonetic mispronunciations and the actual word ratings. Based on phonological rules representing phonetic mispronunciation productions, we propose two approaches to predict the gradation of word mispronunciations. Reasonable correlation and agreement are found between the human-labeled and machine-predicted gradations for both approaches, which imply that the use of phonological rules in word-level mispronunciation gradation prediction is promising.

Index Terms: CAPT, crowdsourcing, mispronunciation gradation

Full Paper

Bibliographic reference.  Wang, Hao / Qian, Xiaojun / Meng, Helen (2013): "Predicting gradation of L2 English mispronunciations using crowdsourced ratings and phonological rules", In SLaTE-2013, 127-131.