Mathematical Modeling of Perception and Acquisition of Temporal Aspects of Speech for Second Language Learners

2017 Fiscal Year Final Research Report

• Project/Area Number: 25330223
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: National Institute of Information and Communications Technology
• Principal Investigator: Kato Hiroaki 国立研究開発法人情報通信研究機構, 先進的音声翻訳研究開発推進センター先進的音声技術研究室, 主任研究員 (20374093)
• Co-Investigator(Renkei-kenkyūsha): SAGISAKA YOSHINORI 早稲田大学, 大学院国際情報通信研究科, 教授 (70339737) ; TAJIMA KEIICHI 法政大学, 文学部, 教授 (70366821)
• Research Collaborator: SONU MEE 日本大学, 文理学部, 助教 ; CHOU ENRYU 早稲田大学, 学生 ; HIRATA YUKARI Colgate University, 教授
• Project Period (FY): 2013-04-01 – 2018-03-31
• Keywords: 知覚認知学習 / 音声言語情報処理 / 聴覚 / 時間的側面 / 韻律 / 音声言語習得 / 国際情報交換 / 韓国：中国：アメリカ

Outline of Final Research Achievements

In order to contribute to learners who learn Japanese as a second language, characteristics related to perception and learning of temporal elements of speech typified by speech rhythms were obtained by empirical methods. This improved the accuracy in objective evaluation using a mathematical model that quantitatively calculates the naturalness of the temporal structures of a given utterance. The results are applicable to wide range of practical usages. For learners of Japanese, for instance, it helps to objectively evaluate their own speech, and for native speakers, it helps to quantitatively evaluate the quality and quantity of communication by analysing given spontaneous conversation from the temporal aspect.

Free Research Field

情報学