Skip to content

Detail of publication


Lukas Machlica and Zbynek Zajic and Ludek Muller : Discriminative adaptation based on fast combination of DMAP and DfMLLR . Interspeech 2010, p. 534-537, ISCA, 2010.

Download PDF



This paper investigates the combination of discriminative adaptation techniques. The discriminative Maximum A-Posteriori (DMAP) adaptation and discriminative feature Maximum Likelihood Linear Regression (DfMLLR) are examined. Since each of the methods is proposed for distinct amount of adaptation data it is useful to combine them in order to preserve the systems performance in situations with varying amount of adaptation data. Generally, DfMLLR and DMAP are executed subsequently (DMAP preceded by DfMLLR) demanding to approach the data twice. Since both methods address the data through the same statistics an one-pass-combination was proposed in order to decrease the time consumption. The one-pass-combination utilizes the advantage of DfMLLR method to transform directly the feature vectors. However, instead of feature vectors the statistics are transformed, what allows to use already computed statistics for the DMAP pass without the need to process the data once again. All the approaches are compared also to their non-discriminative alternatives.

Detail of publication

Title: Discriminative adaptation based on fast combination of DMAP and DfMLLR
Author: Lukas Machlica ; Zbynek Zajic ; Ludek Muller
Language: English
Date of publication: 24 Sep 2010
Year: 2010
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Interspeech 2010
Page: 534 - 537
ISSN: 1990-9772
Publisher: ISCA
/ 2011-03-15 17:39:49 /


MAP, fMLLR, DMAP, DfMLLR, MMI, adaptation, speech recognition, combination


 author = {Lukas Machlica and Zbynek Zajic and Ludek Muller},
 title = {Discriminative adaptation based on fast combination of DMAP and DfMLLR},
 year = {2010},
 publisher = {ISCA},
 journal = {Interspeech 2010},
 pages = {534-537},
 ISSN = {1990-9772},
 url = {},