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/10119/11510

Title: A singing voices synthesis system to characterize vocal registers using ARX-LF model
Authors: Motoda, Hiroki
Akagi, Masato
Issue Date: 2013-03
Publisher: 2013 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'13)
Magazine name: 2013 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'13)
Start page: 93
End page: 96
Abstract: This paper proposes a singing voices synthesis system to synthesize singing voices having characteristics of vocal registers, such as vocal fly, modal and falsetto. Human can sing songs naturally in wide range of frequency by training how to use vocal fold vibrations to represent vocal registers. However, even state-of-the-art singing voices synthesis systems cannot produce vocal registers appropriately. Naturalness of the synthesized singing voices using these systems is reduced in low and high frequency ranges. One of the methods for improving naturalness is adding characteristics of glottal sources for each vocal register. In this paper, the ARX-LF model that can formulate glottal sources for each vocal register by simulating human voice production mechanisms was applied. A model for controlling ARX-LF parameters corresponding to characteristics of glottal sources was constructed, and acoustic features corresponding to naturalness of singing voice were added. Singing voice data of each vocal register were analyzed by the ARX-LF model, and ARX-LF parameter values corresponding to glottal source of each vocal register were obtained. The control model was constructed using the results of the analysis. Singing voices were synthesized by the control model, and quality of the synthesized voices was evaluated. As the results, almost the same impressions were obtained from the synthesized singing voices as those from actual singing voices in each vocal register. Results revealed effectiveness of the proposed system for synthesizing singing voices to characterize vocal registers.
Rights: This material is posted here with permission of the Research Institute of Signal Processing Japan. Hiroki Motoda and Masato Akagi, 2013 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'13), 2013, pp.93-96.
URI: http://hdl.handle.net/10119/11510
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
NCSP2013_Motoda.pdf1524KbAdobe 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