Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016

Fernando Villavicencio, Junichi Yamagishi, Jordi Bonada, Felipe Espic


In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.


DOI: 10.21437/Interspeech.2016-305

Cite as

Villavicencio, F., Yamagishi, J., Bonada, J., Espic, F. (2016) Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016. Proc. Interspeech 2016, 1657-1661.

Bibtex
@inproceedings{Villavicencio+2016,
author={Fernando Villavicencio and Junichi Yamagishi and Jordi Bonada and Felipe Espic},
title={Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-305},
url={http://dx.doi.org/10.21437/Interspeech.2016-305},
pages={1657--1661}
}