2013 Fiscal Year Final Research Report
Singing voice synthesis based on control of acoustical and physiological characteristics
| Project/Area Number |
23700197
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Kanazawa University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Keywords | 歌声合成 / 歌声知覚・生成 / 歌声固有の音響特徴 / オペラ歌唱 / 声区 / 物真似歌唱 / 歌声の類似度 |
|---|
| Research Abstract |
The aim of this study was to develop a singing voice synthesis method that can synthesize artistic and expressive singing voice. Research achievements of the study were followings.(1)A large database which contains 500 singing tracks sung by 25 operatic or pop singers was constructed. (2)A vocal register conversion method between a modal and falsetto registers based on modification of acoustical and physiological characteristics was developed. (3)A operatic singing voice synthesis method based on controlling acoustical characteristics unique to operatic singings was proposed. (4)Acoustic characteristics that define singer individuality (vocal timbre, and way of singing) was examined. These achievements contribute to development of the singing voice synthesis.
|
