Publications -> Journal Papers

An Exemplar-based Approach to Frequency Warping for Voice Conversion


Authors: X. Tian, S. W. Lee, Z. Wu, E. S. Chng, and H. Li
Title: An Exemplar-based Approach to Frequency Warping for Voice Conversion
Abstract: The voice conversion’s task is to modify a source speaker’s voice to sound like that of a target speaker. A conversion method is considered successful when the produced speech sounds natural and similar to the target speaker. This paper presents a new voice conversion framework in which we combine frequency warping and exemplar-based method for voice conversion. Our method maintains high-resolution details during conversion by directly applying frequency warping on the high-resolution spectrum to represent the target. The warping function is generated by a sparse interpolation from a dictionary of exemplar warping functions. As the generated warping function is dependent only on a very small set of exemplars, we do away with the statistical averaging effects inherited from Gaussian mixture models (GMM). To compensate for the conversion error, we also apply residual exemplars into the conversion process. Both objective and subjective evaluations on the VOICES database validated the effectiveness of the proposed voice conversion framework. We observed a significant improvement in speech quality over the state-of-the-art parametric methods.
Keywords: Voice conversion; Exemplar; Sparse representation; Frequency warping; Residual compensation
Journal Name: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 10
Publisher: IEEE
Year: 2017
Accepted PDF File: An_Exemplar-based_Approach_to_Frequency_Warping_for_Voice_Conversion_accepted.pdf
Permanent Link: https://doi.org/10.1109/TASLP.2017.2723721
Reference: X. Tian, S. W. Lee, Z. Wu, E. S. Chng, and H. Li, “An exemplar-based approach to frequency warping for voice conversion,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 10, pp. 1863–1876, October 2017.
bibtex: 
@article {LILY-j51,
    author  = {Tian, Xiaohai and Lee, Siu Wa and Wu, Zhizheng and Chng, Eng Siong and Li, Haizhou},
    title   = {An Exemplar-based Approach to Frequency Warping for Voice Conversion},
    journal  = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    year  = {2017},
    month  = {October},
    volume  = {25},
    number  = {10},
    pages  = {1863-1876},
    publisher  = {IEEE},
 }