A cross-institutional study into speech recognition for language learners, analyzing usage patterns

2021 Fiscal Year Final Research Report

• Project/Area Number: 18K00825
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 02100:Foreign language education-related
• Research Institution: Kanazawa University
• Principal Investigator: Ross Gary 金沢大学, 薬学系, 准教授 (10708142)
• Project Period (FY): 2018-04-01 – 2022-03-31
• Keywords: speech recognition / speech synthesis / autonomy / feedback

Outline of Final Research Achievements

Overall findings suggest the use of Speech Recognition holds merit for improving learning outcomes in language learners. Although the result fell just outside of significance, students tended to score better in tests using Speech Recognition practice than using traditional methods. Furthermore, students were positive about the use of Speech Recognition as a seamless way to practice spoken language. Speech Recognition is a new and improving technology and further long-term work is needed to develop different types of activities (including mobile) and to determine whether these lead to improved learning outcomes.

Free Research Field

Computer Assisted Language Learning

Academic Significance and Societal Importance of the Research Achievements

The lack of speech practice in Japanese L2 classrooms is a serious obstacle to English language education. Lack of spoken and presentation skills affects Japan scientifically and politically. This study shows that Speech Recognition Technology can lead to language and speaking improvement in Japan.