JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/15085

Title: Synthesis of expressive singing voice by F0, amplitude envelope and spectral feature conversion
Authors: Nguyen, Thi-Hao
Akagi, Masato
Issue Date: 2018-03-07
Publisher: Research Institute of Signal Processing, Japan
Magazine name: 2018 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2018)
Start page: 687
End page: 690
Abstract: 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
Material Type: publisher
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
2752.pdf441KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology