One of the key challenges of optimizing a unit selection voice is obtaining suitable target and join cost weights. In this paper we investigate several strategies to train these weights automatically. Two training algorithms are tested, which are based on an acoustic distance that approximates human perception: a modified version of the well-known linear regression training and an iterative algorithm that tries to minimize a selection error. Since a single, global set of weights might not result in selecting all the time the best sequence of units, we investigate whether using multiple weight sets could improve the synthesis quality.
Bibliographic reference. Latacz, Lukas / Mattheyses, Wesley / Verhelst, Werner (2011): "Joint target and join cost weight training for unit selection synthesis", In INTERSPEECH-2011, 321-324.