2016 Fiscal Year Final Research Report
Acoustic scene analysis based on time-space acoustic signal modeling and machine learning
Project/Area Number |
26730100
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Perceptual information processing
|
Research Institution | NTT Communication Science Laboratories |
Principal Investigator |
Kameoka Hirokazu 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, メディア情報研究部, 主任研究員 (20466402)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Keywords | 音響情景分析 / 深層学習 / 多重音解析 / 音響イベント検出 / 音源分離 / 到来方向推定 / 残響除去 / 高速学習アルゴリズム |
Outline of Final Research Achievements |
Humans are able to recognize what kinds of sounds are present and which direction they are emanating from by using their ears. The aim of this work has been to develop a method that let machines imitate this kind of human auditory function through physical modeling of the generative process of acoustic waveforms and probabilistic modeling of human hearing perception.
|
Free Research Field |
音響信号処理
|