Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environments H Boril, JHL Hansen IEEE Transactions on Audio, Speech, and Language Processing 18 (6), 1379-1393, 2009 | 104 | 2009 |
CRSS systems for 2012 NIST speaker recognition evaluation T Hasan, SO Sadjadi, G Liu, N Shokouhi, H Bořil, JHL Hansen 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 92 | 2013 |
Analysis and detection of cognitive load and frustration in drivers' speech H Boril, S Omid Sadjadi, T Kleinschmidt, J Hansen Proceedings of the 11th annual conference of the international speech …, 2010 | 92 | 2010 |
I4U submission to NIST SRE 2012: A large-scale collaborative effort for noise-robust speaker verification R Saeidi, KA Lee, T Kinnunen, T Hasan, B Fauve, PM Bousquet, E Khoury, ... Annual Conference of the International Speech Communication Association …, 2013 | 91 | 2013 |
An investigation on back-end for speaker recognition in multi-session enrollment G Liu, T Hasan, H Boril, JHL Hansen 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 46 | 2013 |
Direct time domain fundamental frequency estimation of speech in noisy conditions H Bořil, P Pollák 2004 12th European Signal Processing Conference, 1003-1006, 2004 | 45 | 2004 |
UT-VOCAL EFFORT II: Analysis and constrained-lexicon recognition of whispered speech S Ghaffarzadegan, H Bořil, JHL Hansen 2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014 | 42 | 2014 |
Generative modeling of pseudo-whisper for robust whispered speech recognition S Ghaffarzadegan, H Bořil, JHL Hansen IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (10 …, 2016 | 38 | 2016 |
Robust speech recognition: Analysis and equalization of Lombard effect in Czech corpora H Boril Czech Technical University in Prague, Czech Republic http://www. utdallas …, 2008 | 38 | 2008 |
Towards multimodal driver’s stress detection H Bořil, P Boyraz, JHL Hansen Digital signal processing for in-vehicle systems and safety, 3-19, 2012 | 32 | 2012 |
UT-Scope: Towards LVCSR under Lombard effect induced by varying types and levels of noisy background H Bořil, JHL Hansen 2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011 | 32 | 2011 |
On the issues of intra-speaker variability and realism in speech, speaker, and language recognition tasks JHL Hansen, H Bořil Speech Communication 101, 94-108, 2018 | 31 | 2018 |
Design and collection of Czech Lombard speech database H Bořil, P Pollák Proc. of Interspeech 5, 1577-1580, 2005 | 27 | 2005 |
Model and feature based compensation for whispered speech recognition S Ghaffarzadegan, H Bořil, JHL Hansen Fifteenth Annual Conference of the International Speech Communication …, 2014 | 26 | 2014 |
Supervector pre-processing for PRSVM-based Chinese and Arabic dialect identification Q Zhang, H Bořil, JHL Hansen 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 24 | 2013 |
Data-driven design of front-end filter bank for Lombard speech recognition H Boril, P Fousek, P Pollák Ninth International Conference on Spoken Language Processing, 2006 | 24 | 2006 |
Speaker height estimation from speech: Fusing spectral regression and statistical acoustic models JHL Hansen, K Williams, H Bořil The Journal of the Acoustical Society of America 138 (2), 1052-1067, 2015 | 23 | 2015 |
Arabic Dialect Identification–‘Is the Secret in the Silence?’and Other Observations H Boril, A Sangwan, JHL Hansen INTERSPEECH-12, 2012 | 23 | 2012 |
UTDrive: Emotion and cognitive load classification for in-vehicle scenarios H Boril, SO Sadjadi, JHL Hansen The 5th Biennial workshop on digital signal processing for in-vehicle …, 2011 | 22 | 2011 |
Deep neural network training for whispered speech recognition using small databases and generative model sampling S Ghaffarzadegan, H Bořil, JHL Hansen International Journal of Speech Technology 20, 1063-1075, 2017 | 20 | 2017 |