Paper Info
Title
Cross-Gender Voice Conversion With Constant F0-Ratio And Average Background Conversion Model
Abstract
This paper presents the method for spectral voice conversion using parallel training data. The proposed solution was submitted to the 2018 Voice Conversion Challenge. The method focuses on the preparation of the generative model for cross-gender voice conversion in differential-filtering framework. To improve the quality of the Gaussian mixture conversion model we introduced the usage of the averaged speaker background model pre-training step. Constant F-0 ratio transformation of source speech using WORLD vocoder was also proposed to improve cross-gender conversion quality. The evaluation results show that the proposed solution outperforms most of the concurrent systems submitted to the 2018 Voice Conversion Challenge, both in terms of speech quality and similarity. The system achieved 76% similarity score and 3.22 mean opinion score in cross-gender conversion task.
Year
DOI
Venue
2019
10.1109/icassp.2019.8683369
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
voice conversion, F-0 transformation, GMM, differential filtering
Training set,Pattern recognition,Computer science,Speech quality,Mean opinion score,Gaussian,Artificial intelligence,Generative model
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
0
3
Name
Order
Citations
PageRank
Zbigniew Latka100.34
Jakub Galka2447.47
Bartosz Ziólko34615.76