EUROSPEECH 2003 - INTERSPEECH 2003 8th European Conference on Speech Communication and Technology Geneva, Switzerland September 1-4, 2003

Combining Non-Uniform Unit Selection with Diphone Based Synthesis

Michael Pucher (1), Friedrich Neubarth (1), Erhard Rank (1), Georg Niklfeld (1), Qi Guan (2)

(1) ftw., Austria
(2) Siemens Osterreich AG, Austria

This paper describes the unit selection algorithm of a speech synthesis system, which selects the k-best paths over units from a relational unit database. The algorithm uses words and diphones as basic unit types. It is part of a customisable text-to-speech system designed for generating new prompts using a recorded speech corpus, with the option that the user can interactively optimise the results from the unit selection algorithm. This algorithm combines advantages of non-uniform unit selection algorithms and diphone inventory based speech synthesis.

Full Paper

Bibliographic reference.  Pucher, Michael / Neubarth, Friedrich / Rank, Erhard / Niklfeld, Georg / Guan, Qi (2003): "Combining non-uniform unit selection with diphone based synthesis", In EUROSPEECH-2003, 1329-1332.