Name
Title | ||
|---|---|---|
Creating German unit selection voices for the MARY TTS platform from the BITS corpora. |
Abstract | ||
|---|---|---|
The present paper reports on the creation of German unit selection voices from corpora which had been recorded and an- notated previously in the BITS project. We describe the unit se- lection mechanism of our MARY TTS platform, as well as the tools for creating a synthesis voice from a speech corpus, and their application to the creation of German unit selection voices from the BITS corpora. Because of reservations concerning the mismatch of phonetic chains predicted by the German TTS components in MARY and the manually corrected database la- bels, we compared voices based on the manually corrected la- bels with voices based on automatic forced alignment labelling. We compute the diphone coverage for both types of voices and show that it is a reasonable approximation of the German di- phone set. A preliminary evaluation confirms the expectations: while the manually corrected versions show a higher segmental accuracy, the automatically labelled versions sound more fluent. |
Year | Venue | DocType |
|---|---|---|
2007 | SSW | Conference |
Citations | PageRank | References |
3 | 0.51 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marc Schröder | 1 | 44 | 5.38 |
| Anna Hunecke | 2 | 3 | 0.51 |