| Title: | Exploring automatic similarity measures for unit selection tuning |
| Authors: | Tihelka, Daniel Romportl, Jan |
| Citation: | TIHELKA, Daniel; ROMPORTL, Jan. Exploring automatic similarity measures for unit selection tuning. In: Proceedings of ICSPL 2009: 10th Annual Conference of the International Speech Communication Association 2009, 6-10 September 2009, Brighton, UK. [Baixas]: ISCA, 2009, p. 736-739. ISSN 1990-9772. |
| Issue Date: | 2009 |
| Publisher: | ISCA |
| Document type: | článek article |
| URI: | http://www.kky.zcu.cz/cs/publications/TihelkaD_2009_ExploringAutomatic http://hdl.handle.net/11025/16974 |
| ISSN: | 1990-9772 |
| Keywords: | syntéza řeči;výběr jednotky;prozodické vzory;vnímaná podobnost |
| Keywords in different language: | speech synthesis;unit selection;prosodic patterns;perceived similarity |
| Abstract in different language: | The present paper focuses on the current handling of target features in the unit selection approach basically requiring huge corpora. In the paper there are outlined possible solutions based on measuring (dis)similarity among prosodic patterns. As the start of research, the feasibility of (dis)similarity estimation is examined on several intuitively chosen measures of acoustic signal which are correlated to perceived similarity obtained from a large-scale listening test. |
| Rights: | © Daniel Tihelka - Jan Romportl |
| Appears in Collections: | Články / Articles (MMI) Články / Articles (NTIS) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| TihelkaD_2009_ExploringAutomatic.pdf | Plný text | 75,66 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/16974Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.