Articulatory speech synthesis
Articulatory speech synthesis is used if the input of this type of synthesiser is a phonetic symbol string and the output is an acoustic speech signal.
A movement pattern is calculated for the model articulators (lips, tongue, velum, glottis) on the basis of a segmental or a gestural production model. Then, the articulator model calculates the geometry of the vocal tract (the area function) for each time instant. Lastly, the aerodynamic-acoustic model calculates the acoustic speech signal.