Přejít na obsah

Detail publikace


Lukáš Machlica and Zbyněk Zajíc and Aleš Pražák : Methods of Unsupervised Adaptation in Online Speech Recognition . SPECOM'2009 Proceedings, p. 448-453, 2009.

PDF ke stažení



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.

Detail publikace

Název: Methods of Unsupervised Adaptation in Online Speech Recognition
Autor: Lukáš Machlica ; Zbyněk Zajíc ; Aleš Pražák
Název - česky: Metody nerizene adaptace v úloze online rozpoznávání řeči
Jazyk publikace: anglicky
Datum vydání: 30.5.2009
Rok vydání: 2009
Typ publikace: Stať ve sborníku
Název časopisu / knihy: SPECOM'2009 Proceedings
Strana: 448 - 453
ISBN: 978-5-8088-0442-5
Datum: 21.6.2009 - 25.6.2009
/ 2009-10-07 13:15:35 /


 author = {Luk\'{a}\v{s} Machlica and Zbyn\v{e}k Zaj\'{i}c and Ale\v{s} Pra\v{z}\'{a}k},
 title = {Methods of Unsupervised Adaptation in Online Speech Recognition},
 year = {2009},
 journal = {SPECOM'2009 Proceedings},
 pages = {448-453},
 ISBN = {978-5-8088-0442-5},
 url = {http://www.kky.zcu.cz/en/publications/LukasMachlica_2009_Methodsof},