Voice Conversion Based on Probabilistic Parameter Transformation and Extended Inter-speaker Residual Prediction

Voice conversion is a process which modifies speech produced by one speaker so that it sounds as if it is uttered by another speaker. In this paper a new voice conversion system is presented. The system requires parallel training data. By using linear prediction analysis, speech is described with line spectral frequencies and the corresponding residua. LSFs are converted together with instantaneous F0 by joint probabilistic function. The residua are transformed by employing residual prediction. In this paper, a new modification of residual prediction is introduced which uses information on the desired target F0 to determine a proper residuum and it also allows an efficient control of F0 in resulting speech.