Speech synthesis method, involves linking added formant waveforms according to pitch interval length and suprasegmental interlinking regulation, and frequency modulating source signals during production of formant waveforms

摘要

The method involves producing formant waveforms by modulation of source signals with an enclosing function (1), where the source signals are oscillated with a formant frequency. The formant waveforms are added, and the added formant waveforms are linked according to a pitch interval length and suprasegmental interlinking regulation to a suprasegmental speech signal. The source signals are frequency modulated during the production of the formant waveforms, where the frequency modulation of the source signals is cyclo-stationary. An independent claim is also included for a speech synthesizer comprising a unit for producing formant waveforms.