2016 Fiscal Year Final Research Report
A study on sound category clustering for auditory scene analysis
Project/Area Number |
26330203
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Perceptual information processing
|
Research Institution | Chiba Institute of Technology |
Principal Investigator |
OKAWA Shigeki 千葉工業大学, 先進工学部, 教授 (40306395)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Keywords | 音環境理解 / 音クラスタリング / 機械学習 / 音環境デザイン |
Outline of Final Research Achievements |
This study focused on "life-log sound", which is various sounds surrounding our life environments, to determine those physical and semantic categories and to discriminate those acoustic events. Our achievements include: (i) defining a method to express the life-log sound mainly based on the subjective evaluation; (ii) investigating and implimenting some algorithms to discriminate sounds based on GMM, DNN, and NMF; (iii) designing a robotic-based method to control the sound, in terms of Auditory Scene Analysis, in a comparatively small space.
|
Free Research Field |
音響情報処理
|