System development of critical situation detection based on sound environment estimation

2018 Fiscal Year Final Research Report

• Project/Area Number: 16K16094
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing
• Research Institution: Ritsumeikan University
• Principal Investigator: Fukumori Takahiro 立命館大学, 情報理工学部, 助教 (60755817)
• Project Period (FY): 2016-04-01 – 2019-03-31
• Keywords: 音環境推定 / 危機検知

Outline of Final Research Achievements

In this study, for detecting critical situation in the house, I have developed an algorithm and an acoustic system that automatically estimate acoustic environments (recognize speech, daily-life sound and abnormal sound) in real time. This system firstly extracts acoustic features that well represent human auditory characteristics from a sound measured by a microphone. After that, the critical degree is evaluated by a deep neural network that is trained with these acoustic features. Then, the result is shown on the computer display.

Free Research Field

音響情報処理

Academic Significance and Societal Importance of the Research Achievements

本研究成果は、叫び声、異常音、報知音を危機として捉えて、音環境を推定できる音響システムを開発しており、高齢者にとどまらず、全ての単身生活者を犯罪や災害などの危機的状況から守る一助となる。特に核家族や単身生活を想定すると、単身生活者と離れて暮らす家族が、当人の生活状況を遠隔地から随時確認することが可能となり、安全安心な生活基盤の形成に貢献できる。さらに、危機的状況を検知することで重大な犯罪を未然に防ぐ効果も期待できる。