Involvement-in-conversation type CALL system

2019 Fiscal Year Final Research Report

• Project/Area Number: 15K02738
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Foreign language education
• Research Institution: Doshisha University
• Principal Investigator: Yamamoto Seiichi 同志社大学, 研究開発推進機構, 嘱託研究員 (20374100)
• Co-Investigator(Kenkyū-buntansha): 馬田 一郎 国立研究開発法人情報通信研究機構, ユニバーサルコミュニケーション研究所多感覚・評価研究室, 研究員 (40374110)
• Project Period (FY): 2015-04-01 – 2020-03-31
• Keywords: 音声認識 / CALL / 自然言語処理

Outline of Final Research Achievements

This research proposed a joining-in-type robot-assisted language learning (JIT-RALL) system as a computer-assisted language learning (CALL) systems with unique features that invites a learner to join in English conversations with two robots. The learner is encouraged to obtain communicative skill in English through implicit learning from dialogues between the robot and tutoring from a teacher robot. Experimental results comparing the ratios that the learners use appropriate expression before and after training with the JIT-RALL system demonstrated that the learners used appropriate expressions significantly more after the training. The experiment results demonstrated that the combination of tutoring and implicit learning implemented in the JIT-RALL system is effective for the learner to facilitate proceduralization of their declarative knowledge and develop their spontaneous productive skills in using grammatical patterns.

Free Research Field

音声認識

Academic Significance and Societal Importance of the Research Achievements

近年のグローバル化を背景として，国際的共通語としての英語でのコミュニケーション能力の習得は一層その重要性を増しており，学習者と対話を行い，発音以外に文法，語彙等のコミュニケーション能力全般の向上を支援するシステムである音声対話型 CALL (DB-CALL)の研究開発が急がれている社会環境で，広範囲な話題を対象としてimplicit learningとtutoringを効果的に組み合わせた音声対話型 CALLシステムを提案し，その実現可能性を実証した意義は大きい．