• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2018 Fiscal Year Final Research Report

Individual-based and automatic clustering of World Englishes and its application to assist international communication

Research Project

  • PDF
Project/Area Number 26240022
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Research Field Perceptual information processing
Research InstitutionThe University of Tokyo

Principal Investigator

Minematsu Nobuaki  東京大学, 大学院工学系研究科(工学部), 教授 (90273333)

Co-Investigator(Kenkyū-buntansha) 牧野 武彦  中央大学, 経済学部, 教授 (00269482)
山内 豊  東京国際大学, 商学部, 教授 (30306245)
齋藤 大輔  東京大学, 大学院工学系研究科(工学部), 講師 (40615150)
Project Period (FY) 2014-04-01 – 2018-03-31
Keywords世界諸英語 / 発音自動分類 / 音声の構造的表象 / 機械学習 / 発音の了解性 / 聴取の頑健性 / 分節的・韻律的特徴 / 韻律読み上げチュータ
Outline of Final Research Achievements

This project primarily focused on pronunciation variation in World Englishes and built 1) a technique of predicting the pronunciation distance between any two English speakers for the purpose of drawing a pronunciation map, and 2) a bird's-eye browser of WE pronunciations with a specific speaker located at the origin of the map. However, it is a fact that two speakers with different pronunciations can not rarely communicate smoothly with each other. Then, we proposed 3) a technique of predicting when native American listeners misunderstand English spoken with Japanese accents. Misunderstanding can happen not only due to accents but to other environmental factors. So, we analyzed 4) what kind of environmental factors easily reduce listening performance of Japanese listeners, and we proposed a method to improve robustness of their listening. Finally, we developed 5) prosodic reading tutor for Japanese learners to improve naturalness and intelligibility of their spoken Japanese.

Free Research Field

音声工学・科学

Academic Significance and Societal Importance of the Research Achievements

本プロジェクトは,英語発音の多様性に着眼し,学習者自らを世界諸英語の中心に据えて,世界諸英語を俯瞰するブラウザを構築し,発音の多様性への意識を向上させる機会を提供した。このような試みはこれまでに例がなく,国内外の関連する学会にて,7回の招待講演,基調講演を行い,学術的に大きく貢献した。また,発音の崩れによる了解性の低下を避けるべく,日本語学習者向けに構築した韻律読み上げチュータは,既に14ヶ国語に翻訳され,世界中の教育機関で使われるに至っている。このシステムは,本プロジェクト開始前から開発を進めていたが,2019年4月時点で,40カ国,140回の講習会を重ねており,社会的意義は極めて高い。

URL: 

Published: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi