Hynek Boril, Ph.D.
Research Associate
Center for Robust Speech Systems (CRSS)
Erik Jonsson School of Engineering and Computer Science
The University of Texas at Dallas
CURRENT ACTIVITIES
-
2-6-2012
ICASSP'12 (Kyoto, Japan)
Will present two papers with my colleagues on front-end processing strategies for robust speech recognition in reverberated conditions and increased vocal effort and on an automatic highlight generation scheme for sports videos. Curious if I'd see any authentic j-pen players :-) 8-31-2011
INTERSPEECH'11 (Florence, Italy)
A paper on improved bottleneck features, co-written with the original author of the bottleneck features. I think that was the baselinest baseline I had ever chance to work with so far, thanks Franta!5-27-2011
ICASSP'11 (Prague, Czech)
Presented a paper on LVCSR on UT-Scope with modified RASTA filter (idea from the trip to INTERSPEECH'10). Beer is still cheaper than water in Czech restaurants. Or, and that's much closer to the truth, water is more expensive than beer in Czech restaurants!10-1-2010
INTERSPEECH'10 (Tokyo, Japan)
Presented two papers on cognitive load/emotion classification in drivers and initial study on excitement level classification for sport video highlights generation. First time in Japan (well, outside Narita). The best sushi ever, amazing Studio Ghibli stuffed animals store, driving on the left hand side in Nagoya,... nice memories.
Welcome To My Homepage
About Me
I was born in Most, Czech Republic. I received the M.S. degree in electrical engineering and Ph.D. degree in electrical engineering and information technology at the Department of Electrical Engineering, Czech Technical University in Prague, in 2003 and 2008, respectively. In August 2007, I joined the Center for Robust Speech Systems (CRSS), Eric Jonsson School of Engineering and Computer Science, University of Texas at Dallas, where I currently work as a Postdoctoral Research Associate. I serve as an external reviewer for the Journal of the Acoustical Society of America (JASA), IEEE Transactions on Audio, Speech and Language Processing (TASLP), Speech Communication (Elsevier Journal), The EURASIP Journal on Audio, Speech, and Music Processing, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE International Conference on Signal Processing and Communications (SPCOM), ISCA INTERSPEECH conference, IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), and IEEE Workshop on Signal Processing Systems (SiPS).
Research Interests
Automatic Speech/Speaker Recognition in Adverse Conditions
- Lombard effect, noise, and channel in speech/speaker recognition
- Robust feature extraction front-ends
- Online feature equalization
- Acoustic modeling for varying environments
- Limited resource speech recognition (migration to foreign dialects)
Speech Analysis/Assessment
- Classification of cognitive load and emotions in drivers
- Classification of Arabic dialects
- Longitudinal characteristics of infant speech development
- Prosody modeling
Music Analysis
- High time-frequency resolution pitch tracking
Last Updated 2-6-2012