Title :
Segmentwise unit selection
Author :
Campillo, F. ; Nozhov, I. ; Banga, E.R.
Author_Institution :
Signal Theor. Group ETSI Ing. de Telecomun., Univ. de Vigo, Vigo, Spain
Abstract :
Unit selection speech systems generate synthetic speech by concatenation of acoustic units extracted from a natural recording. Given a large speech database, the sequence of units with the best global cost is chosen by means of a Viterbi search. In this reported work, it is shown that small subcosts not related to perceptual measures can affect the sequence of units that is finally chosen, with a potential effect on the quality of synthetic speech. A segmentwise unit selection approach that minimises this effect is then proposed.
Keywords :
audio databases; search problems; speech synthesis; Viterbi search; natural recording; segmentwise unit selection; speech database; synthetic speech generation; unit selection speech systems;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2011.0315