Skip to content

Detail of publication


Zbyněk Zajíc and Lukáš Machlica and Luděk Müller : Robust Statistic Estimates for Adaptation in the Task of Speech Recognition . Lecture Notes in Computer Science, vol. 6231/2010, p. 464-471, Springer-Verlag Berlin Heidelberg, 2010.

Download PDF



This paper deals with robust estimations of data statistics used for the adaptation. The statistics are accumulated before the adaptation process from available adaptation data. In general, only small amount of adaptation data is assumed. These data are often corrupted by noise, channel, they do not contain only clean speech. Also, when training Hidden Markov Models (HMM) several assumptions are made that could not have been fulfilled in the praxis, etc. Therefore, we described several techniques that aim to make the adaptation as robust as possible in order to increase the accuracy of the adapted system. One of the methods consists in initialization of the adaptation statistics in order to prevent ill-conditioned transformation matrices. Another problem arises when an acoustic feature is assigned to an improper HMM state even if the reference transcription is available. Such situations can occur because of the forced alignment process used to align frames to states. Thus, it is quite handy to accumulate data statistic utilizing only reliable frames (in the sense of data likelihood). We are focusing on Maximum Likelihood Linear Transformations and the experiments were performed utilizing the feature Maximum Likelihood Linear Regression (fMLLR). Experiments are aimed to describe the behavior of the system extended by proposed methods.

Detail of publication

Title: Robust Statistic Estimates for Adaptation in the Task of Speech Recognition
Author: Zbyněk Zajíc ; Lukáš Machlica ; Luděk Müller
Language: English
Date of publication: 1 Sep 2010
Year: 2010
Type of publication: Papers in journals
Title of journal or book: Lecture Notes in Computer Science
Číslo vydání: 6231/2010
Page: 464 - 471
ISSN: 0302-9743
Publisher: Springer-Verlag Berlin Heidelberg
/ 2011-10-10 10:28:36 /


fMLLR, adaptation, speech recognition, robustness


 author = {Zbyn\v{e}k Zaj\'{i}c and Luk\'{a}\v{s} Machlica and Lud\v{e}k M\"{u}ller},
 title = {Robust Statistic Estimates for Adaptation in the Task of Speech Recognition},
 year = {2010},
 publisher = {Springer-Verlag Berlin Heidelberg},
 journal = {Lecture Notes in Computer Science},
 volume = {6231/2010},
 pages = {464-471},
 ISSN = {0302-9743},
 url = {},