| Title: | Context-dependent ASR: technical report no. DCSE/TR-2009-12 |
| Authors: | Hejtmánek, Jan |
| Issue Date: | 2009 |
| Publisher: | University of West Bohemia in Pilsen |
| Document type: | zpráva report |
| URI: | http://www.kiv.zcu.cz/publications/ http://hdl.handle.net/11025/21578 |
| Keywords: | rozpoznávání řeči;prozodie |
| Keywords in different language: | speech recognition;prosody |
| Abstract in different language: | Computer speech recognition gains more and more attention these days with its implementation in nearly everyday life. But the ultimate goal is still out of reach. The automatic recognition (ASR) systems can very precisely work on small domain. However the bigger the domain is the worse is the performance of the ASR system. The aim of many researchers is to diminish this problem on various levels of the ASR. This work describes components of an ASR system, how they are working together and delves into prosody and how it is used in ASR. From the usage of prosody, the main part of work describes how the ASR can be improved better modeling of the speech variance. We discuss usage of triphones, syllables and other models as well as algorithms and techniques for clustering. |
| Rights: | © University of West Bohemia in Pilsen |
| Appears in Collections: | Zprávy / Reports (KIV) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Hejtmanek.pdf | Plný text | 1,37 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/21578Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.