Improving Preselection in Unit Selection Synthesis

Unit selection synthesis is a method of selecting and concatenating speech segments from a large single-speaker audio database to synthesize utterances. Selection is based on assigning target and concatenation costs to units and then finding a lowest cost sequence of units that will synthesize a given utterance. In order to synthesize efficiently, it is necessary to limit the number of units considered in the unit selection cost network, a part of the process called pre-selection. This paper examines the role of pre-selection in unit selection synthesis. They refine the existing process of pre-selection by adding multiple phone sets to the list of features considered. They present experimental results that demonstrate better database usage and significantly increased synthesis quality using this new method.