Development of an open-source speaking evaluation platform with automated scoring

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K00807
• 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: Kochi University of Technology
• Principal Investigator: Daniels Paul 高知工科大学, 共通教育教室, 教授 (50307245)
• Co-Investigator(Kenkyū-buntansha): 熊井 信弘 学習院大学, 付置研究所, 教授 (00248999)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: automated / speech / assessment / language / learning / speaking

Outline of Final Research Achievements

Successful development of an open-source automated speaking assessment platform was achieved. The platform automated the scoring of speaking tasks, allowed the instructor to add custom speaking tasks, and offered learners individualized speaking feedback. Data collected from student use of the system indicated that student’s overall speaking abilities improved. Learners also indicated that the speaking tasks with individualized feedback was helpful. In addition, a positive correlation was observed between the human-generated and computer-generated scores for speaking tasks.

Free Research Field

Teaching English a a foreign language

Academic Significance and Societal Importance of the Research Achievements

Through the development of an open-source system with automated scoring of speech, language learners in large classes had more opportunities for extensive speaking practice. In addition, the system proved beneficial for speaking practice for standardized language learning tests.