|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/15085
|
| タイトル: | Synthesis of expressive singing voice by F0, amplitude envelope and spectral feature conversion |
| 著者: | Nguyen, Thi-Hao
Akagi, Masato |
| 発行日: | 2018-03-07 |
| 出版者: | Research Institute of Signal Processing, Japan |
| 誌名: | 2018 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2018) |
| 開始ページ: | 687 |
| 終了ページ: | 690 |
| 抄録: | This paper investigates correlates of acoustic features to emotional singing voices. By analyzing acoustic features that are strongly related to emotions, this research determines which feature is more significant to the emotional expressions in singing voices. We also propose a method to modify amplitude envelopes based on the entire F0 contour to have a higher naturalness as singing voice. The results show that the spectral feature is the most affecting acoustic feature to the emotion of singing voice. However, in order to obtain high naturalness and singing-ness for the synthesized voices, it is necessary to manipulate all three features that are F0 contour, amplitude envelope and spectral sequences. |
| Rights: | Copyright (C) 2018 Research Institute of Signal Processing, Japan. Thi-Hao Nguyen and Masato Akagi, 2018 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2018), 2018, 687-690. |
| URI: | http://hdl.handle.net/10119/15085 |
| 資料タイプ: | publisher |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 2752.pdf | | 441Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
