Issues in the design of an advanced unit selection method for natural sounding concatenative synthesis

This paper describes a method for selecting units from a database of recorded speech, for use in a concatenative speech synthesizer. The simplest approach is to store one example of every possible unit. A more powerful method is to have multiple examples of each unit. The challenge for such a method is to provide an efficient means of selecting units from a practical inventory, to give the best approximation to the desired sequence in some clearly specified way. The approach used in BT’s Laureate system uses mixed N‐phone units. In theory, such units could be of arbitrary size, but in practice they are constrained to a maximum of three phones. This method dynamically generates the unit sequence based on a global cost. Units are selected using purely phonologically motivated criteria, without reference to acoustic features, either desired or available within the inventory. A sophisticated method of unit selection does not, however, guarantee natural sounding synthesis. The process of signal generation play...