Name
Abstract | ||
|---|---|---|
The goal of the work described here is to limit the computation needed in unit selection Viterbi search for text-to-speech synthesis. The broader goal is to improve speech quality through the practical use of significantly larger databases. We focus in this paper on trying to reduce the number of concatenation cost calculations. By making certain weak assumptions about f0 distributions we estimate that only a fraction of possible concatenations are relevant. A method for selecting the relevant concatenations by imposing an ordering constraint on candidate units is proposed. The ordering is based on unit f0 value(s). Strengths and weaknesses of this approach are discussed and data is presented about calculation complexity compared with naive Viterbi search. A listening test was conducted to investigate the effect on synthesis quality under various configurations of algorithm and database. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICASSP.2011.5947573 | Acoustics, Speech and Signal Processing |
Keywords | DocType | ISSN |
maximum likelihood estimation,search problems,speech synthesis,Viterbi search,text-to-speech synthesis,unit selection Viterbi network,concatenation costs,speech synthesis,unit selection | Conference | 1520-6149 E-ISBN : 978-1-4577-0537-3 |
ISBN | Citations | PageRank |
978-1-4577-0537-3 | 0 | 0.34 |
References | Authors | |
1 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alistair Conkie | 1 | 264 | 38.03 |
| Ann K. Syrdal | 2 | 244 | 33.00 |