Projects per year
Abstract / Description of output
We present the implementation and evaluation of an open-domain unit selection speech synthesis engine designed to be flexible enough to encourage further unit selection research and allow rapid voice development by users with minimal speech synthesis knowledge and experience. We address the issues of automatically processing speech data into a usable voice using automatic segmentation techniques and how the knowledge obtained at labelling time can be exploited at synthesis time. We describe target cost and join cost implementation for such a system and describe the outcome of building voices with a number of different sized datasets. We show that, in a competitive evaluation, voices built using this technology compare favourably to other systems.
Original language | English |
---|---|
Pages (from-to) | 317-330 |
Number of pages | 14 |
Journal | Speech Communication |
Volume | 49 |
Issue number | 4 |
Early online date | 15 Feb 2007 |
DOIs | |
Publication status | Published - Apr 2007 |
Keywords / Materials (for Non-textual outputs)
- Speech synthesis
- Unit selection
Fingerprint
Dive into the research topics of 'Multisyn: Open-domain unit selection for the Festival speech synthesis system'. Together they form a unique fingerprint.Projects
- 2 Finished
-
-
Expressive Prosody for Unit-selection Speech Synthesis
King, S., Clark, R. & Steedman, M.
UK central government bodies/local authorities, health and hospital authorities
1/01/04 → 29/02/12
Project: Research