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. Index Terms — Language learning, mispronunciation detection, phonetic and phonological analysis 1.

We have developed an English pronunciation learning system which estimates the intelligibility of students ’ speech and ranks their errors from the viewpoint of improving their intelligibility. We have begun using this system in a CALL class at Kyoto University. We have evaluated system performance through the use of questionnaires and analysis of speech data logged in the server, and will present our findings in this paper. 1.

This paper presents a method using speech recognition with linguistic constraints to detect the mispronunciations made by Cantonese learners of English. The predicted pronunciation errors have been derived from cross-language phonological comparisons, which are used to generate the erroneous pronunciation variations in a lexicon. The acoustic models are trained with native speakers ’ speech and used for recognizing the phone sequences, given the orthographic transcriptions. The experiments have examined that the agreement between automatic mispronunciation detection and human judges is over 84 % for 21 Cantonese speakers. Index Terms — mispronunciation detection, phonological comparison, speech recognition 1.

This paper presents a mispronunciation detection system which uses automatic speech recognition to support computer-aided pronunciation training (CAPT). Our methodology extends a model pronunciation lexicon with possible phonetic mispronunciations that may appear in learners ’ speech. Generation of these pronunciation variants was previously achieved by means of phone-tophone mapping rules derived from a cross-language phonological comparison between the primary language (L1, Cantonese) and secondary language (L2, American English). This rule-based generation process results in many implausible candidates of mispronunciation. We present a methodology that applies Viterbi decoding on learners ’ speech using an HMM-based recognizer and the fully extended pronunciation dictionary. Word boundaries are thus identified and all pronunciation variants are scored and ranked based on Viterbi scores. Pruning is applied to keep the N-best pronunciation variants which are deemed plausible candidates for mispronunciation detection. Experiments based on the speech recordings from 21 Cantonese learners of English shows that the agreement between automatic mispronunciation detection and human judges is over 86%. Index Terms: mispronunciation detection, phonological comparison, speech recognition

Abstract—This paper gives an overview of the English and Japanese CALL systems which have been developed at Kyoto University. Both systems incorporate automatic speech recognition (ASR) technologies to detect pronunciation errors. In order to cope with non-native speech, error prediction mechanisms are prepared based on linguistic knowledge and corpus-based decision tree learning. Several choices of acoustic modeling for non-native speech including erroneous pronunciations are also investigated. The English CALL system is designed for Japanese college students so that they can introduce Japanese cultures to foreign people, thus the acoustic model and error prediction are tuned to the specific native language (L1=Japanese). On the other hand, the Japanese CALL system is for foreign visitors of any L1, and focuses on basic-level sentence production and adopts GUI for easy practice. I.

In this paper, we describe an implementation of an intonational quality assessment system for foreign language learning using a handheld portable device. The Viterbi algorithm is employed to conduct the forced alignments that indicate the boundary of each phonemes and a pitch detector is used to extract the intonational features. The tonal pitch type of the segmented syllables is classified and the tendency of the pitch movement is measured. Then, the score of the spoken sentence is generated based on this information. We have implemented this system on an ARM7 RISC processor based system. For real time operation, we applied fixed-point arithmetic to the signal processing kernels and rearranged the algorithm flow of the system. As a result, the system runs in real time on a 60MHz CPU clock frequency. Reference DB