Sixth ISCA Workshop on Speech Synthesis
If a concatenative speech synthesis system uses more short speech segments, it increases the potential to generate natural speech because the concatenation variation becomes greater. Recently, a synthesis approach was proposed in which very short (5 ms) segments are used. In this paper, an implementation of an HMM-based feature generation module into a very short segment concatenative synthesis system that has the advantage of modularity and a synthesis experiment are described.
Full Paper Presentation (ppt) Poster (pdf)
Bibliographic reference. Hirai, Toshio / Yamagishi, Junichi / Tenpaku, Seiichi (2007): "Utilization of an HMM-based feature generation module in 5 ms segment concatenative speech synthesis", In SSW6-2007, 81-84.