Development of English pronunciation software for oral presentations

2016 Fiscal Year Final Research Report

• Project/Area Number: 25370680
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Foreign language education
• Research Institution: Tokyo National College of Technology
• Principal Investigator: HORI Tomoko 東京工業高等専門学校, 一般教育科, 教授 (00269789)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Keywords: 英語プレゼンテーション / 英語音声特徴 / 英語発音学習ソフトウェア

Outline of Final Research Achievements

This study investigated the acoustic characteristics of English oral presentations and developed a computer-based learning system for practicing English pronunciation and prosody to deliver effective presentations. Regarding the acoustic characteristics, we analyzed presentations delivered by native speakers of English using Praat for speaking rate, pauses, and pitch. The system we proposed includes functions such as loading speech sounds, playing the sounds, displaying and altering pitch. We also proposed a voice conversion method based on a Gaussian mixture model, and speech scoring system using pitch and intensity. In addition, we proposed a function which changes the thickness and color of pitch contour to show intensity of the sounds as well.

Free Research Field

英語教育