| Title: | Automatic segmentation for czech concatenative speech synthesis using statistical approach with boundary-specific correction |
| Authors: | Matoušek, Jindřich Tihelka, Daniel Psutka, Josef |
| Citation: | MATOUŠEK, JindŘich; TIHELKA, Daniel; PSUTKA, Josef. Automatic segmentation for czech concatenative speech synthesis using statistical approach with boundary-specific correction. In: Eurospeech 2003 - Interspeech: proceedings of the 8th European Conference on Speech Communication and Technology, 1-4 September 2003, Geneva, Switzerland. [Baixas]: ISCA, 2003, p. 301-304. ISSN 1018-4074. |
| Issue Date: | 2003 |
| Publisher: | ISCA |
| Document type: | článek article |
| URI: | http://hdl.handle.net/11025/17031 http://www.kky.zcu.cz/cs/publications/MatousekJ_2003_Automatic |
| ISSN: | 1018-4074 |
| Keywords: | segmentace řeči s využitím HMM;posouvání HTK hranic;inicializace HMM;hranice specifické pro statistické korekce;objektivní srovnání |
| Keywords in different language: | HMM-based speech segmentation;shifting HTK boundaries;HMM initialization;boundary-specific statistical correction;objective comparison |
| Abstract in different language: | This paper deals with the problems of automatic segmentation for the purposes of Czech concatenative speech synthesis. Statistical approach to speech segmentation using HMMs is applied in the baseline system. Several improvements of this system are then proposed to get more accurate segmentation results. These enhancements mainly concern the various strategies of HMM initialization (flat-start initialization, hand-labeled or speaker independent HMM bootstrapping). Since HTK was utilized in our work, a correction of the output boundary placements is proposed to reflect speech parameterization mechanism. An objective comparison of various automatic methods and manual segmentation is performed to find out the best method. The best results were obtained for boundary-specific statistical correction of the segmentation that resulted from bootstrapping with hand-labeled HMMs (96% segmentation accuracy in tolerance region 20ms). |
| Rights: | © Jindřichich Matoušek - Daniel Tihelka - Josef Psutka |
| Appears in Collections: | Články / Articles (KKY) Články / Articles (NTIS) Články / Articles (KIV) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| MatousekJ_2003_Automatic.pdf | Plný text | 460,92 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/17031Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.