Before continuing, you should check that you have the right background by watching this video.

A short video demonstration of unit selection. You can find the actual interactive demo on this website. Have a play with it yourself!

With multiple candidates available for each target position, a search must be performed.

To choose between the many possible sequences of candidate units, we need to quantify how good each possible sequence will sound.

We use the linguistic specification from the front end to define a target unit sequence. Then, we find all potential candidate units in the database.

Linguistic context affects the acoustic realisation of speech sounds. But several different linguistic contexts can lead to almost the same sound. Unit selection takes advantage of this “interchangeability”.