In this paper, we demonstrate a system implementation of a framework for computer assisted pronunciation training for second language learner (L2). This framework supports an iterative improvement of the automatic pronunciation error recognition and classification by allowing integration of annotated error data. The annotated error data is acquired via an annotation tool for linguists. This pap...

In commercial materials for the teaching of second language (L2) pronunciation, common bottom-up approaches segment phonology into a series discrete and decontextualized linguistic components with rules that students are encouraged to internalize. Such seem out step recent acquisition (SLA) theory research emphasize central influence social context, interlocutor, empathy, nonverbal elements on ...

The current study investigated first language (L1) effects on listener judgment of comprehensibility and accentedness in second language (L2) speech. The participants were 45 university-level adult speakers of English from three L1 backgrounds (Chinese, Hindi, Farsi), performing a picture narrative task. Ten native English listeners used continuous sliding scales to evaluate the speakers’ audio...

This paper presents a new approach to model prototypical foreign-accented pronunciation variants on the phonetic transcription level using rewrite rules. For each native language (L1) and target language (L2) pair, a set of postlexical rules is designed to transform canonical phonetic dictionaries of L2 into adapted dictionaries for native L1 speakers. Potential applications are speech recognit...

This paper presents a new approach for developing pronunciation tutors in Second Language (L2) learning. Applying the Basic Identification of Confusable Contexts (BICC) procedure we automatically generate curriculum that is rich in possible confusion contexts which can be practiced by L2 students in read-aloud tasks. This is the basis of a new pronunciation tutor where the student interacts ora...

This paper presents a new technique in the development of tools for Computer-Aided Language Learning (CALL) in Second Language (L2) pronunciation training. Instead of the usual pinpointing and feedback strategies, which address all production errors in the L2 speaker equally, this technique aims at honing in on where a pronunciation error can lead to a confusion in the transmission of the messa...

The purpose of this study was to investigate the effect of CALL/Web-based instruction on improving EFL learners’ pronunciation ability. To this end, 85 students who were enrolled in a language institute in Rasht were selected as subjects. These students were given the Oxford Placement Test in order to validate their proficiency levels. They were then divided into two groups of 30 and were...

This paper presents a fully automated approach for the recognition of non-native speech based on acoustic model modification. For a native language (L1) and a spoken language (L2), pronunciation variants of the phones of L2 are automatically extracted from an existing non-native database as a confusion matrix with sequences of phones of L1. This is done using L1’s and L2’s ASR systems. This con...