Deriving salient learners’ mispronunciations from cross-language phonological comparisons

This work aims to derive salient mispronunciations made by Chinese (L1 being Cantonese) learners of English (L2 being American English) in order to support the design of pedagogical and remedial instructions. Our approach is grounded on the theory of language transfer and involves systematic phonological comparison between two languages to predict possible phonetic confusions that may lead to mispronunciations. We collect a corpus of speech recordings from some 21 Cantonese learners of English. We develop an automatic speech recognizer by training cross-word triphone models based on the TIMIT corpus. We also develop an "extended" pronunciation lexicon that incorporates the predicted phonetic confusions to generate additional, erroneous pronunciation variants for each word. The extended pronunciation lexicon is used to produce a confusion network in recognition of the English speech recordings of Cantonese learners. We refer to the statistics of the erroneous recognition outputs to derive salient mispronunciations that stipulates the predictions based on phonological comparison.

1. Introduction

The objective of this work is to derive salient mispronunciations made by Cantonese (L 1) learners of English (L2). Our long-term goal is to design effective pedagogical and remedial instructions for pronunciation improvement. The target learners are adults (high school and university students) who are native Cantonese speakers seeking to improve their pronunciation in English. We present a methodology that predicts possible phonetic confusions based on a comparative phonological analysis between L1 and L2. These predicted confusions are incorporated into a pronunciation lexicon to generate additional, erroneous pronunciation variants of each word. The extended pronunciation lexicon is used to produce a confusion network for recognition of English speech recordings of Cantonese learners. We tabulate the statistics of the erroneous recognition outputs to derive salient mispronunciations that stipulates the predictions based on phonological comparison.