Title: | Methods of unsupervised adaptation in online speech recognition |
Other Titles: | Metody neřízené adaptace online rozpoznávání řeči |
Authors: | Machlica, Lukáš Zajíc, Zbyněk Pražák, Aleš |
Citation: | MACHLICA, Lukáš; ZAJÍC, Zbyněk; PRAĹ˝ĂK, Aleš. Methods of unsupervised adaptation in online speech recognition. In: SPECOM 2009 Proceedings. St. Petersburg: Institute for Informatics and Automation of RAS (SPIIRAS), 2009, p. 448-453. ISBN 978-5-8088-0442-5. |
Issue Date: | 2009 |
Publisher: | Institute for Informatics and Automation of RAS (SPIIRAS) |
Document type: | článek article |
URI: | http://www.kky.zcu.cz/cs/publications/LukasMachlica_2009_Methodsof http://hdl.handle.net/11025/17044 |
ISBN: | 978-5-8088-0442-5 |
Keywords: | adaptační techniky;pravděpodobnost lineární transformace |
Keywords in different language: | adaptation techniques;likelihood linear transformations |
Abstract in different language: | This paper deals with adaptation techniques based on maximum likelihood linear transformations, which are well suited for the task of on-line recognition. When transcriptions are available before the system starts running, we are speaking about supervised adaptation. In unsupervised adaptation the transcriptions have to be computed in the first pass of the recognition process. This is often the case in on-line recognition, where data are gathered continuously. Because the system does not work perfectly it is suitable to assign a certainty factor (CF) to each of the transcriptions. Only data that transcriptions have high CF are used for the adaptation. In the on-line recognition, the adaptation (in the sense of updating transformation formulas) has to be performed iteratively whenever the amount of recognized data reaches the pre-specified level. When small amount of adaptation data is available, it is suitable to involve regression trees to cluster similar model parameters. It is quite useful to adapt both speech and silence parameters. Because speech and silence have very different characteristics, we have separated them into two different clusters. Presented methods have been tested on short term recordings and results have proved the suitability of the proposed approach. |
Rights: | © Lukáš Machlica - Zbyněk Zajíc - Aleš Pražák |
Appears in Collections: | Články / Articles (KKY) Články / Articles (NTIS) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
LukasMachlica_2009_Methodsof.pdf | Plný text | 123,85 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/17044
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.