The Mathematical Institute, University of Oxford, Eprints Archive

Voice morphing using the generative topographic mapping

Orphanidou, C. and Moroz, I. M. and Roberts, S. J. (2003) Voice morphing using the generative topographic mapping. In: International Conference on Computer, Communication and Control Technologies, 2003, Florida, USA.

[img]
Preview
PDF
168Kb

Abstract

In this paper we address the problem of Voice Morphing. We attempt to transform the spectral characteristics of a source speaker's speech signal so that the listener would believe that the speech was uttered by a target speaker. The voice morphing system transforms the spectral envelope as represented by a Linear Prediction model. The transformation is achieved by codebook mapping using the Generative Topographic Mapping, a non-linear, latent variable, parametrically constrained, Gaussian Mixture Model.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Best paper in Image, Speech and Signal Computing
Subjects:O - Z > Statistics
D - G > Dynamical systems and ergodic theory
Research Groups:Oxford Centre for Industrial and Applied Mathematics
ID Code:206
Deposited By:Irene Moroz
Deposited On:21 Sep 2005
Last Modified:20 Jul 2009 14:19

Repository Staff Only: item control page