In communication learning by second language, three abilities have to be improved; listening, speaking and writing abilities. In this sense, it is important to evaluate user’s pronunciation ability and to detect mispronunciations in English CALL (Computer-Assisted Language Learning) systems. In this paper, we propose three functions (segmentation, phrasing and pronunciation evaluation) in the C...

The technology developed for task-based spoken dialogue systems (SDS) has a significant potential for Computer-Assisted Language Learning. Based on the CMU Let’s Go SDS, we describe two areas in which we investigated adaptations of the technology to non-native speakers: speech recognition and correction prompt generation. Although difficulties remain, particularly towards robust understanding, ...

In communication learning by second language, three abilities have to be improved; listening, speaking and writing abilities. In this sense, it is important to evaluate user’s pronunciation ability and to detect mispronunciations in English CALL (Computer-Assisted Language Learning) systems. In this paper, we propose three functions (segmentation, phrasing and pronunciation evaluation) in the C...

This study examined the effectiveness of Telegram social network on the writing performance of adult English as foreign language (EFL) learners at intermediate level. To achieve this, Oxford Quick Placement Test (2004) was administered to 46 EFL learners at Zaban-e No language institute in Talesh, Iran. Those who met the selection criterion, i.e., performed one standard deviation above and belo...

あらまし 音声認識・合成に関する技術はこの十年ほどの間に大きな進歩を遂げており,言語学習支援 (CALL) システムに関しても,発音の自動評定や模擬会話訓練などの新たな可能性を広げている.音声分析・認識・合成 技術を利用した CALLには,音韻的な観点と韻律的な観点がある.非母語話者の音声を正確に区分化・認識しな がら,そこに含まれる誤りを検出するためのモデル化には多くの課題がある.本論文では,これらの課題と現在 の方法論に関して概観を行う.まず,発音学習支援における音韻的な発音評定と誤り検出に関して,音声認識技 術に基づく方法について述べる.統計的なアプローチの定式化を行い,非母語話者の音響・発音レベルのモデル 化について述べる.次に,継続長や強勢・トーンなどの韻律的なモデル化と評価について述べる.更に,テキス ト音声合成,分析合成,モーフィングなどの音声合成技術の利用についても述...

In this paper we present the CALLE system, a generic environment for the learning of foreign languages. The intention of CALLE is to be a personal companion for the user, which starts to learn a new language from scratch together with the user. The language student can use CALLE in combination with a textbook to assist him in understanding and translating new texts as well as for the fast retri...

For a long period, Computational Linguistics (CL) and Computer-Assisted Language Learning (CALL) have developed almost entirely independently of each other. A brief historical survey shows that the main reason for this state of affairs was the long preoccupation in CL with the general problem of Natural Language Understanding (NLU). As a consequence, much effort was directed to fields such as M...