Copyright 2009 by Helen Meng Abstract. We describe ongoing research in the development of speech technologies that strives to raise the efficacy of computer-aided pronunciation training, especially for Chinese learners of English. Our approach is grounded on the theory of language transfer and involves a systematic phonological comparison between the primary language (L1 being Chinese) and seco...

The DigLIn project aims at providing concrete solutions for adult literacy students by developing and testing L2 literacy acquisition material in four different languages and by employing Automatic Speech Recognition (ASR) to analyse the learner’s read speech output and provide feedback. We develop the technology, design sample exercises for different languages (Dutch, English, German and Finni...

We used eyetracking, perceptual discrimination, and production tasks to examine the influences of perceptual similarity and linguistic experience on word recognition in nonnative (L2) speech. Eye movements to printed words were tracked while German and Dutch learners of English heard words containing one of three pronunciation variants (/t/, /s/, or /f/) of the interdental fricative /θ/. Irresp...

Accentedness is associated with listeners’ evaluative judgements, which might affect an L2 speaker’s construction of image about linguistic self-worth and competence, described as language (L2) self-esteem. This line inquiry pursued in the study presented this paper, investigates relationship between self-esteem extent to a learner’s pronunciation differs from listener’s representation it – acc...

This study investigated intonation of Japanese sentences spoken by Australian English speakers and the influence of their first language (L1) prosody. The second language (L2) intonation is a complicated product of the L1 transfer at two levels of prosodic hierarchy, at word level and at phrase levels. For each level, the typical error patterns were listed and described in terms of L2 acquisiti...

Computer-Assisted Pronunciation Training System (CAPT) has become an important learning aid in second language (L2) learning. Our approach to CAPT is based on the use of phonological rules to capture language transfer effects that may cause mispronunciations. This paper presents an approach for automatic derivation of phonological rules from L2 speech. The rules are used to generate an extended...

We extend the Goodness of Pronunciation (GOP) algorithm from the conventional GMM-HMM to DNN-HMM and further optimize the GOP measure toward L2 language learners’ accented speech. We evaluate the performance of the new proposed approach at phone-level mispronunciation detection and diagnosis on an L2 English learners’ corpus. Experimental results show that the Equal Error Rate (EER) is improved...