2023 Fiscal Year Final Research Report
Conversation analysis for detecting age-related decline and its evaluation
| Project/Area Number |
19K04934
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 25020:Safety engineering-related
|
|---|
| Research Institution | Osaka Institute of Technology |
|---|
Principal Investigator |
Wakita Yumi 大阪工業大学, ロボティクス&デザイン工学部, 教授 (10590359)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
中藤 良久 九州工業大学, 大学院工学研究院, 教授 (10599955)
松田 千登勢 摂南大学, 看護学部, 教授 (70285328)
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | 加齢による衰え推定 / 日常会話 / 頭部動作の変化量 / 話題の広がり度 / マイクロホン距離 / 会話理解度 |
|---|
| Outline of Final Research Achievements |
1. Development of daily conversation database among elderly people: 22 conversations among elderly people in nursing homes and serviced residences who need daily living assistance. 10 transcriptions of the conversations were also constructed. 15 of the 22 conversations were online conversations.
2.The effectiveness of dynamic features of head motion on speakers and Topic-shift characteristics in daily conversation for age-related decline estimation: We confirmed that the amount of change in head motion during conversation tended to differ between the elderly who received daily living assistance and the elderly who lived independently. Also we confirmed that the Topic-shift characteristics in daily conversation differ between younger and older adults, and can be distinguished in 90.5% of cases between older and younger adults. These results suggests that adding this information to conventional F0 and SPL information for each uttacance will improve the accuracy of estimating decline.
|
| Free Research Field |
音声コミュニケーション
|
| Academic Significance and Societal Importance of the Research Achievements |
【学術的意義】相手の発話の理解度が応答時発声のピッチやパワーの継時変化、会話者の頭部の動きの変化量、話題の広がりなどで推定できたことと、本推定が、年齢や会話手段（対面かオンラインか）に寄らず精度よくできることを確認できたことは、会話音声分析分野にて意義があると思われる．
【社会的意義】高齢者における加齢による衰え度合の推定を行うことを目的とする．認知症に至る前の段階での理解力の低下が日常会話の発話の音響的特徴として現れると仮定し、理解力の僅かな低下を推定可能な技術は、高齢者にいち早く免許返納の時期を促すことができ、高齢ドライバーの事故の減少に貢献すると考える，
|
