Frantisek Grézl

According to our database, Frantisek Grézl authored at least 61 papers between 2002 and 2018.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2018

Residual Memory Networks: Feed-forward approach to learn long temporal dependencies.

Murali Karthick Baskar, Martin Karafiát, Lukás Burget, Karel Veselý, Frantisek Grézl, Jan Honza Cernocký

CoRR, 2018

BUT/Phonexia Bottleneck Feature Extractor.

Anna Silnova, Pavel Matejka, Ondrej Glembek, Oldrich Plchot, Ondrej Novotný, Frantisek Grézl, Petr Schwarz, Lukás Burget, Jan Cernocký

Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop, 2018

Analysis of BUT-PT Submission for NIST LRE 2017.

Oldrich Plchot, Pavel Matejka, Ondrej Novotný, Sandro Cumani, Alicia Lozano-Diez, Josef Slavícek, Mireia Díez, Frantisek Grézl, Ondrej Glembek, Mounika Kamsali, Anna Silnova, Lukás Burget, Lucas Ondel, Santosh Kesiraju, Johan Rohdin

Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop, 2018

BUT OpenSAT 2017 Speech Recognition System.

Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Vladimír Malenovský, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Analysis of Multilingual Blstm Acoustic Model on Low and High Resource Languages.

Martin Karafiát, Murali Karthick Baskar, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Multilingually trained bottleneck features in spoken language recognition.

Radek Fér, Pavel Matejka, Frantisek Grézl, Oldrich Plchot, Karel Veselý, Jan Honza Cernocký

Comput. Speech Lang., 2017

2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based Adaptation.

Martin Karafiát, Murali Karthick Baskar, Pavel Matejka, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Residual memory networks: Feed-forward approach to learn long-term temporal dependencies.

Murali Karthick Baskar, Martin Karafiát, Lukás Burget, Karel Veselý, Frantisek Grézl, Jan Cernocký

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Investigation of Bottle-Neck Features for Emotion Recognition.

Anna Popková, Filip Povolný, Pavel Matejka, Ondrej Glembek, Frantisek Grézl, Jan Honza Cernocký

Proceedings of the Text, Speech, and Dialogue - 19th International Conference, 2016

Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting.

Frantisek Grézl, Martin Karafiát

Proceedings of the SLTU-2016, 2016

Study of Large Data Resources for Multilingual Training and System Porting.

Frantisek Grézl, Ekaterina Egorova, Martin Karafiát

Proceedings of the SLTU-2016, 2016

Analysis of the DNN-based SRE systems in multi-language conditions.

Ondrej Novotný, Pavel Matejka, Ondrej Glembek, Oldrich Plchot, Frantisek Grézl, Lukás Burget, Jan Honza Cernocký

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Multilingual BLSTM and speaker-specific vector adaptation in 2016 but babel system.

Martin Karafiát, Murali Karthick Baskar, Pavel Matejka, Karel Veselý, Frantisek Grézl, Jan Cernocký

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Boosting performance on low-resource languages by standard corpora: An analysis.

Frantisek Grézl, Martin Karafiát

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Analysis of DNN approaches to speaker identification.

Pavel Matejka, Ondrej Glembek, Ondrej Novotný, Oldrich Plchot, Frantisek Grézl, Lukás Burget, Jan Cernocký

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Multilingual region-dependent transforms.

Martin Karafiát, Lukás Burget, Frantisek Grézl, Karel Veselý, Jan Honza Cernocký

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Three ways to adapt a CTS recognizer to unseen reverberated speech in BUT system for the ASpIRE challenge.

Martin Karafiát, Frantisek Grézl, Lukás Burget, Igor Szöke, Jan Cernocký

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Multilingual bottleneck features for language recognition.

Radek Fér, Pavel Matejka, Frantisek Grézl, Oldrich Plchot, Jan Cernocký

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Robust speech recognition in unknown reverberant and noisy conditions.

Roger Hsiao, Jeff Z. Ma, William Hartmann, Martin Karafiát, Frantisek Grézl, Lukás Burget, Igor Szöke, Jan Cernocký, Shinji Watanabe, Zhuo Chen, Sri Harish Reddy Mallidi, Hynek Hermansky, Stavros Tsakalidis, Richard M. Schwartz

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

Adapting multilingual neural network hierarchy to a new language.

Frantisek Grézl, Martin Karafiát

Proceedings of the 4th Workshop on Spoken Language Technologies for Under-resourced Languages, 2014

But ASR system for BABEL Surprise evaluation 2014.

Martin Karafiát, Karel Veselý, Igor Szöke, Lukás Burget, Frantisek Grézl, Mirko Hannemann, Jan Cernocký

Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014

Further investigation into multilingual training and adaptation of stacked bottle-neck neural network structure.

Frantisek Grézl, Ekaterina Egorova, Martin Karafiát

Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014

BUT 2014 Babel system: analysis of adaptation in NN based systems.

Martin Karafiát, Frantisek Grézl, Karel Veselý, Mirko Hannemann, Igor Szöke, Jan Cernocký

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Combination of multilingual and semi-supervised training for under-resourced languages.

Frantisek Grézl, Martin Karafiát

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Calibration and fusion of query-by-example systems - But SWS 2013.

Igor Szöke, Lukás Burget, Frantisek Grézl, Jan Cernocký, Lucas Ondel

Proceedings of the IEEE International Conference on Acoustics, 2014

But neural network features for spontaneous Vietnamese in BABEL.

Martin Karafiát, Frantisek Grézl, Mirko Hannemann, Jan Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2014

Adaptation of multilingual stacked bottle-neck neural network structure for new language.

Frantisek Grézl, Martin Karafiát, Karel Veselý

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

BUT SWS 2013 - Massive Parallel Approach.

Igor Szöke, Lukás Burget, Frantisek Grézl, Lucas Ondel

Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop, 2013

BUT BABEL system for spontaneous Cantonese.

Martin Karafiát, Frantisek Grézl, Mirko Hannemann, Karel Veselý, Jan Cernocký

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Score normalization and system combination for improved keyword spotting.

Damianos G. Karakos, Richard M. Schwartz, Stavros Tsakalidis, Le Zhang, Shivesh Ranjan, Tim Ng, Roger Hsiao, Guruprasad Saikumar, Ivan Bulyko, Long Nguyen, John Makhoul, Frantisek Grézl, Mirko Hannemann, Martin Karafiát, Igor Szöke, Karel Veselý, Lori Lamel, Viet Bac Le

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

Discriminative semi-supervised training for keyword search in low resource languages.

Roger Hsiao, Tim Ng, Frantisek Grézl, Damianos G. Karakos, Stavros Tsakalidis, Long Nguyen, Richard M. Schwartz

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

Semi-supervised bootstrapping approach for neural network feature extractor training.

Frantisek Grézl, Martin Karafiát

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

2012

Comparison of methods for language-dependent and language-independent query-by-example spoken term detection.

Javier Tejedor, Michal Fapso, Igor Szöke, Jan Cernocký, Frantisek Grézl

ACM Trans. Inf. Syst., 2012

Transcribing Meetings With the AMIDA Systems.

Thomas Hain, Lukás Burget, John Dines, Philip N. Garner, Frantisek Grézl, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiát, Mike Lincoln, Vincent Wan

IEEE Trans. Speech Audio Process., 2012

The language-independent bottleneck features.

Karel Veselý, Martin Karafiát, Frantisek Grézl, Milos Janda, Ekaterina Egorova

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

Patrol Team Language Identification System for DARPA RATS P1 Evaluation.

Pavel Matejka, Oldrich Plchot, Mehdi Soufifar, Ondrej Glembek, Luis Fernando D'Haro, Karel Veselý, Frantisek Grézl, Jeff Z. Ma, Spyros Matsoukas, Najim Dehak

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2011

The Role of Neural Network Size in TRAP/HATS Feature Extraction.

Frantisek Grézl

Proceedings of the Text, Speech and Dialogue - 14th International Conference, 2011

Integrating Recent MLP Feature Extraction Techniques into TRAP Architecture.

Frantisek Grézl, Martin Karafiát

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Front-End Compensation Methods for LVCSR Under Lombard Effect.

Hynek Boril, Frantisek Grézl, John H. L. Hansen

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Convolutive Bottleneck Network features for LVCSR.

Karel Veselý, Martin Karafiát, Frantisek Grézl

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

Study of probabilistic and Bottle-Neck features in multilingual environment.

Frantisek Grézl, Martin Karafiát, Milos Janda

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Acoustic keyword spotter - optimization from end-user perspective.

Igor Szöke, Frantisek Grézl, Jan Cernocký, Michal Fapso, Tomás Cipr

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

Parallel training of neural networks for speech recognition.

Karel Veselý, Lukás Burget, Frantisek Grézl

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Hierarchical neural net architectures for feature extraction in ASR.

Frantisek Grézl, Martin Karafiát

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

2009

Investigation into bottle-neck features for meeting speech recognition.

Frantisek Grézl, Martin Karafiát, Lukás Burget

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

2008

Optimizing bottle-neck features for lvcsr.

Frantisek Grézl, Petr Fousek

Proceedings of the IEEE International Conference on Acoustics, 2008

2007

Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006.

Niko Brümmer, Lukás Burget, Jan Cernocký, Ondrej Glembek, Frantisek Grézl, Martin Karafiát, David A. van Leeuwen, Pavel Matejka, Petr Schwarz, Albert Strasheim

IEEE Trans. Speech Audio Process., 2007

TRAP-Based Techniques for Recognition of Noisy Speech.

Frantisek Grézl, Jan Cernocký

Proceedings of the Text, Speech and Dialogue, 10th International Conference, 2007

Spoken Term Detection System Based on Combination of LVCSR and Phonetic Search.

Igor Szöke, Michal Fapso, Martin Karafiát, Lukás Burget, Frantisek Grézl, Petr Schwarz, Ondrej Glembek, Pavel Matejka, Jirí Kopecký, Jan Cernocký

Proceedings of the Machine Learning for Multimodal Interaction , 2007

STBU System for the NIST 2006 Speaker Recognition Evaluation.

Pavel Matejka, Lukás Burget, Petr Schwarz, Ondrej Glembek, Martin Karafiát, Frantisek Grézl, Jan Cernocký, David A. van Leeuwen, Niko Brummer, Albert Strasheim

Proceedings of the IEEE International Conference on Acoustics, 2007

Probabilistic and Bottle-Neck Features for LVCSR of Meetings.

Frantisek Grézl, Martin Karafiát, Stanislav Kontar, Jan Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2007

2006

Robust Heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition.

Martin Karafiát, Frantisek Grézl, Petr Schwarz, Lukás Burget, Jan Cernocký

Proceedings of the Machine Learning for Multimodal Interaction, 2006

Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons.

Andreas Stolcke, Frantisek Grézl, Mei-Yuh Hwang, Xin Lei, Nelson Morgan, Dimitra Vergyri

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Further Progress in Meeting Recognition: The ICSI-SRI Spring 2005 Speech-to-Text Evaluation System.

Andreas Stolcke, Xavier Anguera, Kofi Boakye, Özgür Çetin, Frantisek Grézl, Adam Janin, Arindam Mandal, Barbara Peskin, Chuck Wooters, Jing Zheng

Proceedings of the Machine Learning for Multimodal Interaction, 2005

Improved MLP structures for data-driven feature extraction for ASR.

Qifeng Zhu, Barry Y. Chen, Frantisek Grézl, Nelson Morgan

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

2004

Combinations of TRAP Based Systems.

Frantisek Grézl

Proceedings of the Text, Speech and Dialogue, 7th International Conference, 2004

TRAP based features for LVCSR of meting data.

Frantisek Grézl, Martin Karafiát, Jan Cernocký

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

New nonsense syllables database - analyses and preliminary ASR experiments.

Petr Fousek, Frantisek Grézl, Hynek Hermansky, Petr Svojanovsky

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

2003

Local Time-Frequency Operators in TRAPs for Speech Recognition.

Frantisek Grézl

Proceedings of the Text, Speech and Dialogue, 6th International Conference, 2003

Local averaging and differentiating of spectral plane for TRAP-based ASR.

Frantisek Grézl, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

2002

Qualcomm-ICSI-OGI features for ASR.

André Gustavo Adami, Lukás Burget, Stéphane Dupont, Harinath Garudadri, Frantisek Grézl, Hynek Hermansky, Pratibha Jain, Sachin S. Kajarekar, Nelson Morgan, Sunil Sivadas

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002