| Title: | Structural data-driven prosody model for TTS synthesis |
| Other Titles: | Strukturální datový model prozodie pro TTS syntézu |
| Authors: | Romportl, Jan |
| Citation: | ROMPORTL, Jan. Structural data-driven prosody model for TTS synthesis. In: Proceedings of the Speech Prosody 2006 Conference: 3rd International Conference on Speech Prosody, Dresden, Germany, 2-5 May 2006. Dresden: TUDpress, 2006, p. 549-552. ISSN 0940-6832. |
| Issue Date: | 2006 |
| Publisher: | TUDpress |
| Document type: | článek article |
| URI: | http://www.kky.zcu.cz/cs/publications/RomportlJ_2006_Structural http://hdl.handle.net/11025/16990 |
| ISSN: | 0940-6832 |
| Keywords: | prozodie;syntéza řeči;gramatika;model |
| Keywords in different language: | prosody;speech synthesis;grammar;model |
| Abstract: | Tento článek představuje nov datový model prozodie pro účely text-to-speech systému ARTIC. Model je navržen tak, aby byl co nejvíce jazykově nezávislý a generoval přirozenou intonaci s vazbou na sémantiku. Je založen na parametrizaci textu pomocí nové prozodické gramatiky a metod automatické analýzy řečových korpusů. |
| Abstract in different language: | This paper introduces a new data-driven prosody model for the text-to-speech system ARTIC. The model is intended to be almost language-independent and to generate naturally sounding intonation with a link to semantics. It is based on text parametrisation using a new prosodic grammar and on automatic speech corpora analysis methods. Its performance is evaluated by results of presented listening tests. |
| Rights: | © Jan Romportl |
| Appears in Collections: | Články / Articles (MMI) Články / Articles (KKY) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| RomportlJ_2006_Structural.pdf | Plný text | 76,53 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/16990Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.