The present invention relates to a device and method at speech synthesis. A speech is registered and polyphones are stored. In connection with registration of the polyphones also the movement pattern in a face is registered. The registration of the movement pattern in the face is made by that a number of measuring points in the face are registered at the same time as the polyphones are registered. In connection with translation of a person's speech from one language into another, the polyphones and corresponding movement patterns in the face are linked up to a movement model in the face. The face of the real person is after that pasted over the model, at which one to the language corresponding movement pattern is obtained. The invention consequently gives the impression that the person really speaks the language in question. IMAGE
展开▼
