Possibilities and Developments in the Use of Speech Synthesis for People with Visual Impairments to Enjoy Movies

2022 Fiscal Year Final Research Report

• Project/Area Number: 17K01553
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Rehabilitation science/Welfare engineering
• Research Institution: Akita University
• Principal Investigator: Nakajima Sawako 秋田大学, 理工学研究科, 講師 (40453542)
• Co-Investigator(Kenkyū-buntansha): 大河内 直之 東京大学, 先端科学技術研究センター, 特任研究員 (30361679) ; 水戸部 一孝 秋田大学, 理工学研究科, 教授 (60282159)
• Project Period (FY): 2017-04-01 – 2023-03-31
• Keywords: 視覚障害者支援 / 映画・映像 / 音声ガイド / 音声合成 / ヒューマンインタフェース

Outline of Final Research Achievements

In response to this global trend, this study explored ways to improve the movie experience for people with visual impairments and to promote the use of audio description (AD) through the use of speech synthesis and speech rate conversion technologies. Comparative experiments between human AD and synthesized AD showed that synthesized AD has advantages such as being audible and causing little discomfort even at high speech rates. It is necessary to exploit these advantages of synthesized speech and accelerate the production of AD. Therefore, AD production software using speech synthesis has been developed, and problems and opportunities have been identified through demonstration experiments.

Free Research Field

福祉情報工学

Academic Significance and Societal Importance of the Research Achievements

視覚障害者を対象とした映画の音声ガイドの聞き取り実験，および，調査からは，視覚障害者の聴覚特性に関する基礎的知見を得ることができた．視覚障害者が日常生活を送る上で合成音声による情報収集は欠かせない．視覚障害者の感覚や意見からは，今後，社会が合成音声などの技術をどのように活用していくか，新しい音声表現の可能性を得る上で重要な視点を得られた．また，音声合成を用いた音声ガイド制作ソフトは，実証実験を通じて課題を抽出し，また，改善したことで，音声ガイド制作現場で利用価値の高い技術となった．