A new approach of voice conversion based on the GMM model

Authors:
A. Guerid;A. Houacine
Affiliations:
d'Electronique et Informatique, Alia, BabEzzouar, Alger, ALGERIE;d'Electronique et Informatique, Alia, BabEzzouar, Alger, ALGERIE
Venue:
Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology
Year:
2012

Citing 4
Cited 0

Local models and Gaussian mixture models for statistical data processing

Local models and Gaussian mixture models for statistical data processing
High-resolution voice transformation

High-resolution voice transformation
Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02
Performance of Voice Conversion Systems Based on GMM and Applied to Arabic Language

ICMENS '09 Proceedings of the 2009 Fifth International Conference on MEMS NANO, and Smart Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Voice transformation is a process of changing voice personality; i.e. speech uttered by a source speaker is modified to sound as if a target speaker had uttered it. In this paper we study a new approach based on the GMM model and using the first and the second derivate of the pitch and the spectrum as additional information to calculate the joint probability of the source and target. We use the standard Arabic to measure the performance of this new approach.