Abstract | ||
---|---|---|
The purpose of this paper is to examine some aspects of unitselection for Text to Speech synthesis (TTS). We use UnitSelection as described in [2],[3]. The approach taken was tosynthesize a large number of sentences and capture informationabout the selected units. We used approximately 25million phonemes resulting from 10,000 files of AP newswiretext. Given these statistics we looked at the units selected inorder to try to analyse how unit selection works from a statisticalpoint of... |
Year | Venue | Field |
---|---|---|
1999 | EUROSPEECH | Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Natural language processing |
DocType | Citations | PageRank |
Conference | 9 | 1.31 |
References | Authors | |
3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mark C. Beutnagel | 1 | 91 | 11.44 |
Alistair Conkie | 2 | 264 | 38.03 |