2016 Fiscal Year Final Research Report
Research on accumulation and reuse of musical operations
| Project/Area Number |
25700036
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (A)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Research Field |
Entertainment and game informatics 1
|
|---|
| Research Institution | Kyoto University (2014-2016)
University of Tsukuba (2013) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Keywords | 音楽理論GTTM / 音楽構造分析 / グルーピング構造 / 拍節構造 / タイムスパン木 / メロディモーフィング |
|---|
| Outline of Final Research Achievements |
Our goal is to create a system that will enable a musical novice to manipulate a piece of music, which is an ambiguous and subjective media, according to his or her intentions. The main advantage of analysis by a GTTM is that it can acquire tree structures called time-span trees. A time-span tree provides a summarization of a piece of music, which can be used as the representation of an abstraction, resulting in a music retrieval system. It can also be used for performance rendering and reproducing music. The time-span tree can also be used for melody prediction and melody morphing. These systems need a GTTM analyzer that enables us to output the results obtained from analysis that are the same as those obtained by musicologists. In this study, we developed groping structure and metrical structure analyzer based on deep learning. Experimental result shows that the analyzer shows high performance. We plan to implement time-span reduction analysis on the bases of deep learning.
|
| Free Research Field |
音楽情報知能
|
