Development of qualitative language literacy assessment tool for children with autism spectrum disorder based on voice analysis of free conversation prosody

2021 Fiscal Year Final Research Report

• Project/Area Number: 19K12911
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 90150:Medical assistive technology-related
• Research Institution: Kyoto Women's University (2021); University of Miyazaki (2019-2020)
• Principal Investigator: Nakai Yasushi 京都女子大学, 発達教育学部, 准教授 (80462050)
• Co-Investigator(Kenkyū-buntansha): 大歳 太郎 関西医療大学, 保健医療学部, 教授 (40336483)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 自閉スペクトラム症 / プロソディ / 自由会話 / 質的言語能力

Outline of Final Research Achievements

We repeated machine learning of voice patterns in children with autism spectrum disorders and children with typical development. By repeating trial and error with the combination of multidimensional features of pitch, it became almost clear that some features did not affect the discrimination accuracy between children with autism spectrum disorders and children with typical development. However, the collected voice data is not sufficient, so it is necessary to continue to consider it. In addition, it was partially supported that quantifying and objectively evaluating promotes the outcome of the learning program.

Free Research Field

人間医工学

Academic Significance and Societal Importance of the Research Achievements

近年、自閉スペクトラム症のバイオマーカーを探索する研究が散見される。しかし、これらの手法は人体への侵襲性及び機器が設置された場所での実施に限定される。私たちが提案する手法は自閉スペクトラム症児の話し言葉を音声収録用マイクで収集するのみである。人体への侵襲性は皆無であり、音声収録用マイクを含む音声収録機材は持ち運びが簡易である。発話パフォーマンスと脳機能の関係性を検討する中で、適切な学習プログラムを開発すれば、質的言語発達促進を期待できることが考えられた。