Voice conversion is a procedure for converting the voice characteristics of a speech signal. In this paper we propose a technique for voice conversion using artificial neural networks. A backpropagation network is used to capture a transformation function which maps the formants extracted from the speech of the source speaker to that of the target speaker. An average pilch transformation is used to transform the pitch of the source speaker. Speech with the voice characteristics of the target speaker is synthesized using the transformed parameters. © ESCA Workshop on Automatic Speaker Recognition, Identification, and Verification, ASRIV 1994. All rights reserved.