Skip to content

Detail of publication


Zelinka Jan and Šmídl Luboš and Trmal Jan and Müller Luděk : Posterior Estimates and Transforms for Speech Recognition . Lecture Notes in Artificial Intelligence, vol. 2010, p. 480-487, Springer, Heidelberg, 2010.


This paper describes ANN based posterior estimates and their application to speech recognition. We replaced the standard back-propagation with the L-BFGS quasi-Newton method. We have focused only on posterior based feature vector extraction. Our goal was a feature vector dimension reduction. Thus we designed three posterior transforms to space with dimensionality 1 or 2. The designed transforms were tested on the SpeechDat-East corpus. We also applied the introduced method on a Czech audio-visual corpus. In both cases the methods leads to significant word error rate decrease.

Detail of publication

Title: Posterior Estimates and Transforms for Speech Recognition
Author: Zelinka Jan ; Šmídl Luboš ; Trmal Jan ; Müller Luděk
Language: English
Year: 2010
Type of publication: Papers in journals
Title of journal or book: Lecture Notes in Artificial Intelligence
Číslo vydání: 2010
Page: 480 - 487
ISSN: 0302-9743
Publisher: Springer
Address: Heidelberg
2011-03-15 16:21:58 / 2011-03-15 16:21:58 / 1




 author = {Zelinka Jan and \v{S}m\'{i}dl Lubo\v{s} and Trmal Jan and M\"{u}ller Lud\v{e}k},
 title = {Posterior Estimates and Transforms for Speech Recognition},
 year = {2010},
 publisher = {Springer},
 journal = {Lecture Notes in Artificial Intelligence},
 address = {Heidelberg},
 volume = {2010},
 pages = {480-487},
 ISSN = {0302-9743},
 url = {},