Publications -> Conference Papers

System Fusion for High-Performance Voice Conversion

Authors: X. Tian, Z. Wu, S. W. Lee, Q. H. Nguyen, M. Dong, and E. S. Chng
Title: System Fusion for High-Performance Voice Conversion
Abstract: Recently, a number of voice conversion methods have been developed. These methods attempt to improve conversion performance by using diverse mapping techniques in various acoustic domains, e.g. high-resolution spectra and low-resolution Mel-cepstral coefficients. Each individual method has its own pros and cons. In this paper, we introduce a system fusion framework, which leverages and synergizes the merits of these state-of-the-art and even potential future conversion methods. For instance, methods delivering high speech quality are fused with methods capturing speaker characteristics, bringing another level of performance gain. To examine the feasibility of the proposed framework, we select two state-of-the-art methods, Gaussian mixture model and frequency warping based systems, as a case study. Experimental results reveal that the fusion system outperforms each individual method in both objective and subjective evaluation, and demonstrate the effectiveness of the proposed fusion framework.
Keywords: Voice conversion; System fusion; High-performance; Frequency warping; GMM
Conference Name: INTERSPEECH 2015
Location: Dresden, Germany
Publisher: ISCA
Year: 2015
Accepted PDF File: System_Fusion_for_High-Performance_Voice_Conversion_accepted.pdf
Permanent Link:
Reference: X. Tian, Z. Wu, S. W. Lee, Q. H. Nguyen, M. Dong, and E. S. Chng, “System fusion for high-performance voice conversion,” in Proceedings of INTERSPEECH 2015. ISCA, September 2015, pp. 2759–2763.
   author	= {Tian, Xiaohai and Wu, Zhizheng and Lee, Siu Wa and Nguyen, Quy Hy and Dong, Minghui and Chng, Eng Siong},
   title	= {System Fusion for High-Performance Voice Conversion},  
   booktitle	= {Proceedings of INTERSPEECH 2015}, 
   year		= {2015}, 
   month	= {September}, 
   pages	= {2759-2763}, 
   location	= {Dresden, Germany},
   publisher	= {ISCA},