Spoken language acquisition process analysis focusing prosody based on emotion and intention labeling
Project/Area Number |
25330192
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Perceptual information processing
|
Research Institution | Shizuoka University |
Principal Investigator |
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
Keywords | 音声言語発達 / 感情意図ラベリング / マルチモーダル行動分析 / 母子インタラクション / コミュニケーションスキル / 音声言語獲得 / マルチモーダル / 行動コーパス / 韻律 |
Outline of Final Research Achievements |
Aiming to build computational model of development process of human natural intelligence, we have constructed an interaction behavior analysis environment focused on spoken language development of infants, whose core method is utterance analysis based on emotion and intention labels. We have created multimodal utterance emotion behavior database including about 13,000 behavior labels for 500 minutes movie data of mother-child interaction scenes of picture book reading. We have obtained many valuable findings about communication skills of mothers to promote spoken language development of children. We have also proved that the proposed behavior analysis environment is useful to visualize the features of human behavior in communication scenes on multiple domains.
|
Report
(4 results)
Research Products
(6 results)