Martin Karafiát

ORCID

Publication Activity (10 Years)

Years Active: 2002-2023
Publications (10 Years): 31

Top Venues

Publications

Martin Karafiát, Karel Veselý, Igor Szöke, Ladislav Mosner, Karel Benes, Marcin Witkowski, Germán Barchi, Leonardo Pepino
BUT CHiME-7 system description. CoRR (2023)
Martin Kocour, Jahnavi Umesh, Martin Karafiát, Jan Svec, Fernando López, Jordi Luque, Karel Benes, Mireia Díez, Igor Szöke, Karel Veselý, Lukás Burget, Jan Cernocký
BCN2BRNO: ASR System Fusion for Albayzin 2022 Speech to Text Challenge. IberSPEECH (2022)
Martin Kocour, Guillermo Cámbara, Jordi Luque, David Bonet, Mireia Farrús, Martin Karafiát, Karel Veselý, Jan Cernocký
BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge. IberSPEECH (2021)
Hari Krishna Vydana, Martin Karafiát, Lukás Burget, Jan Cernocký
THE IWSLT 2021 BUT SPEECH TRANSLATION SYSTEMS. IWSLT (2021)
Martin Kocour, Guillermo Cámbara, Jordi Luque, David Bonet, Mireia Farrús, Martin Karafiát, Karel Veselý, Jan Honza Cernocký
BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge. CoRR (2021)
Hari Krishna Vydana, Martin Karafiát, Katerina Zmolíková, Lukás Burget, Honza Cernocký
Jointly Trained Transformers Models for Spoken Language Translation. ICASSP (2021)
Hari Krishna Vydana, Martin Karafiát, Lukás Burget, Honza Cernocký
The IWSLT 2021 BUT Speech Translation Systems. CoRR (2021)
Martin Karafiát, Karel Veselý, Jan Honza Cernocký, Ján Profant, Jirí Nytra, Miroslav Hlavácek, Tomás Pavlícek
Analysis of X-Vectors for Low-Resource Speech Recognition. ICASSP (2021)
Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Hari Krishna Vydana, Karel Veselý, Jan Honza Cernocký
BUT Opensat 2019 Speech Recognition System. CoRR (2020)
Hari Krishna Vydana, Martin Karafiát, Katerina Zmolíková, Lukás Burget, Honza Cernocký
Jointly Trained Transformers models for Spoken Language Translation. CoRR (2020)
Murali Karthick Baskar, Lukás Burget, Shinji Watanabe, Martin Karafiát, Takaaki Hori, Jan Honza Cernocký
Promising Accurate Prefix Boosting for Sequence-to-sequence ASR. ICASSP (2019)
Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe, Takaaki Hori, Matthew Wiesner, Jan Cernocký
Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems. INTERSPEECH (2019)
Murali Karthick Baskar, Martin Karafiát, Lukás Burget, Karel Veselý, Frantisek Grézl, Jan Honza Cernocký
Residual Memory Networks: Feed-forward approach to learn long temporal dependencies. CoRR (2018)
Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe, Takaaki Hori, Matthew Wiesner, Jan Honza Cernocký
Analysis of Multilingual Sequence-to-Sequence speech recognition systems. CoRR (2018)
Martin Karafiát, Murali Karthick Baskar, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký
Analysis of Multilingual Blstm Acoustic Model on Low and High Resource Languages. ICASSP (2018)
Bhargav Pulugundla, Murali Karthick Baskar, Santosh Kesiraju, Ekaterina Egorova, Martin Karafiát, Lukás Burget, Jan Cernocký
BUT System for Low Resource Indian Language ASR. INTERSPEECH (2018)
Murali Karthick Baskar, Lukás Burget, Shinji Watanabe, Martin Karafiát, Takaaki Hori, Jan Honza Cernocký
Promising Accurate Prefix Boosting for sequence-to-sequence ASR. CoRR (2018)
Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Vladimír Malenovský, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký
BUT OpenSAT 2017 Speech Recognition System. INTERSPEECH (2018)
Jaejin Cho, Murali Karthick Baskar, Ruizhi Li, Matthew Wiesner, Sri Harish Reddy Mallidi, Nelson Yalta, Martin Karafiát, Shinji Watanabe, Takaaki Hori
Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling. CoRR (2018)
Jaejin Cho, Murali Karthick Baskar, Ruizhi Li, Matthew Wiesner, Sri Harish Mallidi, Nelson Yalta, Martin Karafiát, Shinji Watanabe, Takaaki Hori
Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling. SLT (2018)
Martin Karafiát, Murali Karthick Baskar, Pavel Matejka, Karel Veselý, Frantisek Grézl, Lukás Burget, Jan Cernocký
2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based Adaptation. INTERSPEECH (2017)
Pavlos Papadopoulos, Ruchir Travadi, Colin Vaz, Nikolaos Malandrakis, Ulf Hermjakob, Nima Pourdamghani, Michael Pust, Boliang Zhang, Xiaoman Pan, Di Lu, Ying Lin, Ondrej Glembek, Murali Karthick Baskar, Martin Karafiát, Lukás Burget, Mark Hasegawa-Johnson, Heng Ji, Jonathan May, Kevin Knight, Shrikanth S. Narayanan
Team ELISA System for DARPA LORELEI Speech Evaluation 2016. INTERSPEECH (2017)
Murali Karthick Baskar, Martin Karafiát, Lukás Burget, Karel Veselý, Frantisek Grézl, Jan Cernocký
Residual memory networks: Feed-forward approach to learn long-term temporal dependencies. ICASSP (2017)
Martin Karafiát, Murali Karthick Baskar, Pavel Matejka, Karel Veselý, Frantisek Grézl, Jan Cernocký
Multilingual BLSTM and speaker-specific vector adaptation in 2016 but babel system. SLT (2016)
Martin Karafiát, Lukás Burget, Frantisek Grézl, Karel Veselý, Jan Honza Cernocký
Multilingual region-dependent transforms. ICASSP (2016)
Miroslav Skácel, Martin Karafiát, Lucas Ondel, Albert Uchytil, Igor Szöke
BUT Zero-Cost Speech Recognition 2016 System Description. MediaEval (2016)
Karel Veselý, Shinji Watanabe, Katerina Zmolíková, Martin Karafiát, Lukás Burget, Jan Honza Cernocký
Sequence summarizing neural network for speaker adaptation. ICASSP (2016)
Katerina Zmolíková, Martin Karafiát, Karel Veselý, Marc Delcroix, Shinji Watanabe, Lukás Burget, Jan Cernocký
Data Selection by Sequence Summarizing Neural Network in Mismatch Condition Training. INTERSPEECH (2016)
Frantisek Grézl, Martin Karafiát
Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting. SLTU (2016)
Frantisek Grézl, Ekaterina Egorova, Martin Karafiát
Study of Large Data Resources for Multilingual Training and System Porting. SLTU (2016)
Frantisek Grézl, Martin Karafiát
Boosting performance on low-resource languages by standard corpora: An analysis. SLT (2016)
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
Robust speech recognition in unknown reverberant and noisy conditions. ASRU (2015)
Martin Karafiát, Frantisek Grézl, Lukás Burget, Igor Szöke, Jan Cernocký
Three ways to adapt a CTS recognizer to unseen reverberated speech in BUT system for the ASpIRE challenge. INTERSPEECH (2015)
Frantisek Grézl, Martin Karafiát
Adapting multilingual neural network hierarchy to a new language. SLTU (2014)
Martin Karafiát, Frantisek Grézl, Karel Veselý, Mirko Hannemann, Igor Szöke, Jan Cernocký
BUT 2014 Babel system: analysis of adaptation in NN based systems. INTERSPEECH (2014)
Frantisek Grézl, Ekaterina Egorova, Martin Karafiát
Further investigation into multilingual training and adaptation of stacked bottle-neck neural network structure. SLT (2014)
Tim Ng, Roger Hsiao, Le Zhang, Damianos G. Karakos, Sri Harish Reddy Mallidi, Martin Karafiát, Karel Veselý, Igor Szöke, Bing Zhang, Long Nguyen, Richard M. Schwartz
Progress in the BBN keyword search system for the DARPA RATS program. INTERSPEECH (2014)
Frantisek Grézl, Martin Karafiát, Karel Veselý
Adaptation of multilingual stacked bottle-neck neural network structure for new language. ICASSP (2014)
Frantisek Grézl, Martin Karafiát
Combination of multilingual and semi-supervised training for under-resourced languages. INTERSPEECH (2014)
Martin Karafiát, Frantisek Grézl, Mirko Hannemann, Jan Cernocký
But neural network features for spontaneous Vietnamese in BABEL. ICASSP (2014)
Martin Karafiát, Karel Veselý, Igor Szöke, Lukás Burget, Frantisek Grézl, Mirko Hannemann, Jan Cernocký
But ASR system for BABEL Surprise evaluation 2014. SLT (2014)
Ekaterina Egorova, Karel Veselý, Martin Karafiát, Milos Janda, Jan Cernocký
Manual and semi-automatic approaches to building a multilingual phoneme set. ICASSP (2013)
Martin Karafiát, Frantisek Grézl, Mirko Hannemann, Karel Veselý, Jan Cernocký
BUT BABEL system for spontaneous Cantonese. INTERSPEECH (2013)
Shakti P. Rath, Lukás Burget, Martin Karafiát, Ondrej Glembek, Jan Cernocký
A region-specific feature-space transformation for speaker adaptation and singularity analysis of jacobian matrix. INTERSPEECH (2013)
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
Score normalization and system combination for improved keyword spotting. ASRU (2013)
Petr Motlícek, Daniel Povey, Martin Karafiát
Feature and score level combination of subspace Gaussinas in LVCSR task. ICASSP (2013)
Frantisek Grézl, Martin Karafiát
Semi-supervised bootstrapping approach for neural network feature extractor training. ASRU (2013)
Shakti P. Rath, Martin Karafiát, Ondrej Glembek, Jan Cernocký
A factorized representation of FMLLR transform based on QR-decomposition. INTERSPEECH (2012)
Oldrich Plchot, Martin Karafiát, Niko Brümmer, Ondrej Glembek, Pavel Matejka, Edward de Villiers, Jan Cernocký
Speaker vectors from subspace Gaussian mixture model as complementary features for language identification. Odyssey (2012)
Daniel Povey, Mirko Hannemann, Gilles Boulianne, Lukás Burget, Arnab Ghoshal, Milos Janda, Martin Karafiát, Stefan Kombrink, Petr Motlícek, Yanmin Qian, Korbinian Riedhammer, Karel Veselý, Ngoc Thang Vu
Generating exact lattices in the WFST framework. ICASSP (2012)
Stefan Kombrink, Tomás Mikolov, Martin Karafiát, Lukás Burget
Improving language models for ASR using translated in-domain data. ICASSP (2012)
Karel Veselý, Martin Karafiát, Frantisek Grézl, Milos Janda, Ekaterina Egorova
The language-independent bottleneck features. SLT (2012)
Niko Brümmer, Sandro Cumani, Ondrej Glembek, Martin Karafiát, Pavel Matejka, Jan Pesán, Oldrich Plchot, Mehdi Soufifar, Edward de Villiers, Jan Cernocký
Description and analysis of the Brno276 system for LRE2011. Odyssey (2012)
Thomas Hain, Lukás Burget, John Dines, Philip N. Garner, Frantisek Grézl, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiát, Mike Lincoln, Vincent Wan
Transcribing Meetings With the AMIDA Systems. IEEE Trans. Speech Audio Process. 20 (2) (2012)
Martin Karafiát, Milos Janda, Jan Cernocký, Lukás Burget
Region dependent linear transforms in multilingual speech recognition. ICASSP (2012)
Sandro Cumani, Oldrich Plchot, Martin Karafiát
Independent component analysis and MLLR transforms for speaker identification. ICASSP (2012)
Milos Janda, Martin Karafiát, Jan Cernocký
Dealing with Numbers in Grapheme-Based Speech Recognition. TSD (2012)
Ondrej Glembek, Lukás Burget, Pavel Matejka, Martin Karafiát, Patrick Kenny
Simplification and optimization of i-vector extraction. ICASSP (2011)
Frantisek Grézl, Martin Karafiát, Milos Janda
Study of probabilistic and Bottle-Neck features in multilingual environment. ASRU (2011)
Anoop Deoras, Tomás Mikolov, Stefan Kombrink, Martin Karafiát, Sanjeev Khudanpur
Variational approximation of long-span language models for lvcsr. ICASSP (2011)
Karel Veselý, Martin Karafiát, Frantisek Grézl
Convolutive Bottleneck Network features for LVCSR. ASRU (2011)
Stefan Kombrink, Tomás Mikolov, Martin Karafiát, Lukás Burget
Recurrent Neural Network Based Language Modeling in Meeting Recognition. INTERSPEECH (2011)
Frantisek Grézl, Martin Karafiát
Integrating Recent MLP Feature Extraction Techniques into TRAP Architecture. INTERSPEECH (2011)
Daniel Povey, Martin Karafiát, Arnab Ghoshal, Petr Schwarz
A symmetrization of the Subspace Gaussian Mixture Model. ICASSP (2011)
Martin Karafiát, Lukás Burget, Pavel Matejka, Ondrej Glembek, Jan Cernocký
iVector-based discriminative adaptation for automatic speech recognition. ASRU (2011)
Daniel Povey, Lukás Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
The subspace Gaussian mixture model - A structured model for speech recognition. Comput. Speech Lang. 25 (2) (2011)
Zdenek Jancik, Oldrich Plchot, Niko Brümmer, Lukás Burget, Ondrej Glembek, Valiantsina Hubeika, Martin Karafiát, Pavel Matejka, Tomás Mikolov, Albert Strasheim, Jan Cernocký
Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system. Odyssey (2010)
Martin Karafiát, Igor Szöke, Jan Cernocký
Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data. TSD (2010)
Mirko Hannemann, Stefan Kombrink, Martin Karafiát, Lukás Burget
Similarity scoring for recognizing repeated out-of-vocabulary words. INTERSPEECH (2010)
Tomás Mikolov, Martin Karafiát, Lukás Burget, Jan Cernocký, Sanjeev Khudanpur
Recurrent neural network based language model. INTERSPEECH (2010)
Thomas Hain, Lukás Burget, John Dines, Philip N. Garner, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiát, Mike Lincoln, Vincent Wan
The AMIDA 2009 meeting transcription system. INTERSPEECH (2010)
Lukás Burget, Petr Schwarz, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Daniel Povey, Ariya Rastrow, Richard C. Rose, Samuel Thomas
Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models. ICASSP (2010)
Frantisek Grézl, Martin Karafiát
Hierarchical neural net architectures for feature extraction in ASR. INTERSPEECH (2010)
Nagendra Goel, Samuel Thomas, Mohit Agarwal, Pinar Akyazi, Lukás Burget, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Martin Karafiát, Daniel Povey, Ariya Rastrow, Richard C. Rose, Petr Schwarz
Approaches to automatic lexicon learning with limited training examples. ICASSP (2010)
Richard C. Rose, Atta Norouzian, Aarthi M. Reddy, André Coy, Vishwa Gupta, Martin Karafiát
Subword-based spoken term detection in audio course lectures. ICASSP (2010)
Arnab Ghoshal, Daniel Povey, Mohit Agarwal, Pinar Akyazi, Lukás Burget, Kai Feng, Ondrej Glembek, Nagendra Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
A novel estimation of feature-space MLLR for full-covariance models. ICASSP (2010)
Daniel Povey, Lukás Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
Subspace Gaussian Mixture Models for speech recognition. ICASSP (2010)
Philip N. Garner, John Dines, Thomas Hain, Asmaa El Hannani, Martin Karafiát, Danil Korchagin, Mike Lincoln, Vincent Wan, Le Zhang
Real-time ASR from meetings. INTERSPEECH (2009)
Stefan Kombrink, Lukás Burget, Pavel Matejka, Martin Karafiát, Hynek Hermansky
Posterior-based out of vocabulary word detection in telephone speech. INTERSPEECH (2009)
Frantisek Grézl, Martin Karafiát, Lukás Burget
Investigation into bottle-neck features for meeting speech recognition. INTERSPEECH (2009)
Lukás Burget, Michal Fapso, Valiantsina Hubeika, Ondrej Glembek, Martin Karafiát, Marcel Kockmann, Pavel Matejka, Petr Schwarz, Jan Cernocký
BUT system for NIST 2008 speaker recognition evaluation. INTERSPEECH (2009)
Jirí Kopecký, Ondrej Glembek, Martin Karafiát
Advances in Acoustic Modeling for the Recognition of Czech. TSD (2008)
Martin Karafiát, Lukás Burget, Thomas Hain, Jan Cernocký
Discrimininative training of narrow band - wide band adapted systems for meeting recognition. INTERSPEECH (2008)
Frantisek Grézl, Martin Karafiát, Stanislav Kontar, Jan Cernocký
Probabilistic and Bottle-Neck Features for LVCSR of Meetings. ICASSP (4) (2007)
Martin Karafiát, Lukás Burget, Jan Cernocký, Thomas Hain
Application of CMLLR in narrow band wide band adapted systems. INTERSPEECH (2007)
Thomas Hain, Vincent Wan, Lukás Burget, Martin Karafiát, John Dines, Jithendra Vepa, Giulia Garau, Mike Lincoln
The AMI System for the Transcription of Speech in Meetings. ICASSP (4) (2007)
Igor Szöke, Michal Fapso, Martin Karafiát, Lukás Burget, Frantisek Grézl, Petr Schwarz, Ondrej Glembek, Pavel Matejka, Jirí Kopecký, Jan Cernocký
Spoken Term Detection System Based on Combination of LVCSR and Phonetic Search. MLMI (2007)
Niko Brümmer, Lukás Burget, Jan Cernocký, Ondrej Glembek, Frantisek Grézl, Martin Karafiát, David A. van Leeuwen, Pavel Matejka, Petr Schwarz, Albert Strasheim
Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006. IEEE Trans. Speech Audio Process. 15 (7) (2007)
Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, David A. van Leeuwen, Mike Lincoln, Vincent Wan
The 2007 AMI(DA) System for Meeting Transcription. CLEAR (2007)
Pavel Matejka, Lukás Burget, Petr Schwarz, Ondrej Glembek, Martin Karafiát, Frantisek Grézl, Jan Cernocký, David A. van Leeuwen, Niko Brummer, Albert Strasheim
STBU System for the NIST 2006 Speaker Recognition Evaluation. ICASSP (4) (2007)
Michal Fapso, Pavel Smrz, Petr Schwarz, Igor Szöke, Milan Schwarz, Jan Cernocký, Martin Karafiát, Lukás Burget
Information Retrieval from Spoken Documents. CICLing (2006)
Martin Karafiát, Frantisek Grézl, Petr Schwarz, Lukás Burget, Jan Cernocký
Robust Heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition. MLMI (2006)
Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, Mike Lincoln, Jithendra Vepa, Vincent Wan
The AMI Meeting Transcription System: Progress and Performance. MLMI (2006)
Lukás Burget, Jan Cernocký, Michal Fapso, Martin Karafiát, Pavel Matejka, Petr Schwarz, Pavel Smrz, Igor Szöke
Indexing and Search Methods for Spoken Documents. TSD (2006)
Thomas Hain, John Dines, Giulia Garau, Martin Karafiát, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals
Transcription of conference room meetings: an investigation. INTERSPEECH (2005)
Igor Szöke, Petr Schwarz, Pavel Matejka, Lukás Burget, Martin Karafiát, Michal Fapso, Jan Cernocký
Comparison of keyword spotting approaches for informal continuous speech. INTERSPEECH (2005)
Thomas Hain, Lukás Burget, John Dines, Iain McCowan, Giulia Garau, Martin Karafiát, Mike Lincoln, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals
The Development of the AMI System for the Transcription of Speech in Meetings. MLMI (2005)
Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, Mike Lincoln, Iain McCowan, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals
The 2005 AMI System for the Transcription of Speech in Meetings. MLMI (2005)
Igor Szöke, Petr Schwarz, Pavel Matejka, Lukás Burget, Martin Karafiát, Jan Cernocký
Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech. TSD (2005)
Frantisek Grézl, Martin Karafiát, Jan Cernocký
TRAP based features for LVCSR of meting data. INTERSPEECH (2004)

Martin Karafiát.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Martin Karafiát