F0 Control Model for Mandarin Singing Voice Synthesis

An F0 control model that can control F0 fluctuations and generate natural F0 contours of singing-voices are shown. A Mandarin singing synthesis system is built. The system employs a concatenation-based text-to-speech method to synthesize arbitrary lyrics in Mandarin. Using information contained in a score file, the system concatenates and modifies units from an inventory of 414 syllables, originally recorded in reading style, to form arbitrary lyrical singing voice.