On Voice Characteristics Conversion

Text-to-speech systems available today generate virtually unlimited speech from a prestored component sounds library, which is frequently created from a male voice. A major reason for that is due to the low pitch profile in the male voice. For example, the speech analysis software and commercial synthesizers seem to work more accurately and better with the male voice than the female voice. To overcome the analysis and synthesis problem on the female voice and to provide the choices of having more than one sex of voices output from a text-to-speech system, some means of voice characteristics conversion is needed. To do so, it is important to first understand what parameters in speech define the perception of different sex. An attempt is underway herein to first study these parameters and then to learn to adjust them so that the voice of one sex can be converted to another or from one voice character to another. The voice characteristics conversion technique described herein is best suited for speech systems either a text-to-speech or analysis-synthesis (meaning record-playback) using LPC synthesizers.