Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/89623
Title: An automatic voice conversion evaluation strategy based on perceptual background noise distortion and speaker similarity
Authors: Huang, Dong-Yan
Xie, Lei
Zhang, Shaofei
Lee, Yvonne Siu Wa
Wu, Jie
Ming, Huaiping
Tian, Xiaohai
Ding, Chuang
Li, Mei
Nguyen, Quy Hy
Dong, Minghui
Chng, Eng Siong
Li, Haizhou
Keywords: Engineering::Computer science and engineering
Voice Conversion
Objective Measures
Issue Date: 2016
Source: Huang, D.-Y., Xie, L., Lee, Y. S. W., Wu, J., Ming, H., Tian, X., … Li, H. (2016). An automatic voice conversion evaluation strategy based on perceptual background noise distortion and speaker similarity. 9th ISCA Speech Synthesis Workshop. doi:10.21437/SSW.2016-8
Abstract: Voice conversion aims to modify the characteristics of one speaker to make it sound like spoken by another speaker without changing the language content. This task has attracted considerable attention and various approaches have been proposed since two decades ago. The evaluation of voice conversion approaches, usually through time-intensive subject listening tests, requires a huge amount of human labor. This paper proposes an automatic voice conversion evaluation strategy based on perceptual background noise distortion and speaker similarity. Experimental results show that our automatic evaluation results match the subjective listening results quite well. We further use our strategy to select best converted samples from multiple voice conversion systems and our submission achieves promising results in the voice conversion challenge (VCC2016).
URI: https://hdl.handle.net/10356/89623
http://hdl.handle.net/10220/49691
DOI: https://dx.doi.org/10.21437/SSW.2016-8
Rights: © 2016 International Speech Communication Association (ISCA). All rights reserved. This paper was published in 9th ISCA Speech Synthesis Workshop and is made available with permission of International Speech Communication Association (ISCA).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
ssw9_2016.pdf845.15 kBAdobe PDFThumbnail
View/Open

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.