V Psutka Josef

发表

LVCSR system for automatic online subtitling

Luděk Müller, Aleš Pražák, V Psutka Josef, 2005 .

Comparison between GMM and decision graphs based silence/speech detection method

Jan Zelinka, Luděk Müller, Jan Trmal, 2006 .

Gender-dependent acoustic models fusion developed for automatic subtitling of Parliament meetings broadcasted by the Czech TV

V Psutka Josef, Vaněk Jan, 2010 .

Czech broadcast news speech

Vlasta Radová, Luděk Müller, Josef Psutka, 2004 .

Russian Spontaneaous Speech – Acoustic&Language Models (MALACH)

Josef Psutka, Pavel Ircing, V Psutka Josef, 2005 .

Recognition of spontaneous speech - some problems and their solutions

Josef Psutka, Pavel Ircing, Jan Hoidekr, 2006 .

Keyword spotting with triphone based filler model

Luboš Šmídl, V Psutka Josef, J. Zahradil, 2005 .

Czech broadcast news transcripts

Vlasta Radová, Luděk Müller, Pavel Ircing, 2004 .

Slovak Spontaneaous Speech – Acoustic&Language Models (MALACH)

Josef Psutka, Pavel Ircing, V Psutka Josef, 2006 .

Building robust PLP-based acoustic module for ASR applications

Luděk Müller, V Psutka Josef, 2005 .

Training of Speaker-Clustered Discriminative Acoustic Models for Use in Real-Time Recognizers

V Psutka Josef, Vaněk Jan, Zelinka Jan, 2010 .

Optimization of some parameters in the speech-processing module developed for the speaker independent ASR system

Luděk Müller, V Psutka Josef, 2003 .

Training of Speaker-Clustered Acoustic Models for Use in Real-Time Recognizers

V Psutka Josef, Vaněk Jan, Zelinka Jan, 2009, SIGMAP 2009.

Benefit of maximum likelihood linear transform (MLLT) used at different levels of covariance matrices clustering in ASR systems

V Psutka Josef, 2007 .