default search action
Martin Karafiát
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
- [i9]Martin Karafiát, Karel Veselý, Igor Szöke, Ladislav Mosner, Karel Benes, Marcin Witkowski, Germán Barchi, Leonardo Pepino:
BUT CHiME-7 system description. CoRR abs/2310.11921 (2023) - 2022
- [c89]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: 276-280 - 2021
- [c88]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 - [c87]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: 6998-7002 - [c86]Hari Krishna Vydana, Martin Karafiát, Katerina Zmolíková
Jointly Trained Transformers Models for Spoken Language Translation. ICASSP 2021: 7513-7517 - [c85]Hari Krishna Vydana, Martin Karafiát, Lukás Burget, Jan Cernocký:
The IWSLT 2021 BUT Speech Translation Systems. IWSLT 2021: 75-83 - [i8]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 abs/2101.12729 (2021) - [i7]Hari Krishna Vydana, Martin Karafiát, Lukás Burget, Honza Cernocký:
The IWSLT 2021 BUT Speech Translation Systems. CoRR abs/2107.06155 (2021) - 2020
- [i6]Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Hari Krishna Vydana, Karel Veselý, Jan Honza Cernocký:
BUT Opensat 2019 Speech Recognition System. CoRR abs/2001.11360 (2020) - [i5]Hari Krishna Vydana, Martin Karafiát, Katerina Zmolíková, Lukás Burget, Honza Cernocký:
Jointly Trained Transformers models for Spoken Language Translation. CoRR abs/2004.12111 (2020)
2010 – 2019
- 2019
- [c84]Murali Karthick Baskar, Lukás Burget
Promising Accurate Prefix Boosting for Sequence-to-sequence ASR. ICASSP 2019: 5646-5650 - [c83]Martin Karafiát
Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems. INTERSPEECH 2019: 2220-2224 - 2018
- [c82]Martin Karafiát, Murali Karthick Baskar, Karel Veselý, Frantisek Grézl, Lukás Burget
Analysis of Multilingual Blstm Acoustic Model on Low and High Resource Languages. ICASSP 2018: 5789-5793 - [c81]Martin Karafiát
BUT OpenSAT 2017 Speech Recognition System. INTERSPEECH 2018: 2638-2642 - [c80]Bhargav Pulugundla, Murali Karthick Baskar, Santosh Kesiraju
BUT System for Low Resource Indian Language ASR. INTERSPEECH 2018: 3182-3186 - [c79]Jaejin Cho, Murali Karthick Baskar, Ruizhi Li, Matthew Wiesner, Sri Harish Mallidi, Nelson Yalta
Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling. SLT 2018: 521-527 - [i4]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 abs/1808.01916 (2018) - [i3]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 abs/1810.03459 (2018) - [i2]Murali Karthick Baskar, Lukás Burget, Shinji Watanabe, Martin Karafiát, Takaaki Hori, Jan Honza Cernocký:
Promising Accurate Prefix Boosting for sequence-to-sequence ASR. CoRR abs/1811.02770 (2018) - [i1]Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe, Takaaki Hori, Matthew Wiesner, Jan Honza Cernocký:
Analysis of Multilingual Sequence-to-Sequence speech recognition systems. CoRR abs/1811.03451 (2018) - 2017
- [c78]Murali Karthick Baskar, Martin Karafiát
Residual memory networks: Feed-forward approach to learn long-term temporal dependencies. ICASSP 2017: 4810-4814 - [c77]Martin Karafiát
2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based Adaptation. INTERSPEECH 2017: 719-723 - [c76]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
Team ELISA System for DARPA LORELEI Speech Evaluation 2016. INTERSPEECH 2017: 2053-2057 - [p1]Martin Karafiát, Karel Veselý, Katerina Zmolíková
Training Data Augmentation and Data Selection. New Era for Robust Speech Recognition, Exploiting Deep Learning 2017: 245-260 - 2016
- [c75]Karel Veselý, Shinji Watanabe
Sequence summarizing neural network for speaker adaptation. ICASSP 2016: 5315-5319 - [c74]Martin Karafiát
Multilingual region-dependent transforms. ICASSP 2016: 5430-5434 - [c73]Katerina Zmolíková
Data Selection by Sequence Summarizing Neural Network in Mismatch Condition Training. INTERSPEECH 2016: 2354-2358 - [c72]Miroslav Skácel, Martin Karafiát, Lucas Ondel, Albert Uchytil, Igor Szöke:
BUT Zero-Cost Speech Recognition 2016 System Description. MediaEval 2016 - [c71]Frantisek Grézl, Martin Karafiát
Boosting performance on low-resource languages by standard corpora: An analysis. SLT 2016: 629-636 - [c70]Martin Karafiát
Multilingual BLSTM and speaker-specific vector adaptation in 2016 but babel system. SLT 2016: 637-643 - [c69]Frantisek Grézl, Ekaterina Egorova, Martin Karafiát
Study of Large Data Resources for Multilingual Training and System Porting. SLTU 2016: 15-22 - [c68]Frantisek Grézl, Martin Karafiát
Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting. SLTU 2016: 144-151 - 2015
- [c67]Roger Hsiao, Jeff Z. Ma, William Hartmann, Martin Karafiát
Robust speech recognition in unknown reverberant and noisy conditions. ASRU 2015: 533-538 - [c66]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: 2454-2458 - 2014
- [c65]Martin Karafiát
But neural network features for spontaneous Vietnamese in BABEL. ICASSP 2014: 5622-5626 - [c64]Frantisek Grézl, Martin Karafiát
Adaptation of multilingual stacked bottle-neck neural network structure for new language. ICASSP 2014: 7654-7658 - [c63]Frantisek Grézl, Martin Karafiát:
Combination of multilingual and semi-supervised training for under-resourced languages. INTERSPEECH 2014: 820-824 - [c62]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: 959-963 - [c61]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: 3002-3006 - [c60]Frantisek Grézl, Ekaterina Egorova, Martin Karafiát
Further investigation into multilingual training and adaptation of stacked bottle-neck neural network structure. SLT 2014: 48-53 - [c59]Martin Karafiát
But ASR system for BABEL Surprise evaluation 2014. SLT 2014: 501-506 - [c58]Frantisek Grézl, Martin Karafiát:
Adapting multilingual neural network hierarchy to a new language. SLTU 2014: 39-45 - 2013
- [c57]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
Score normalization and system combination for improved keyword spotting. ASRU 2013: 210-215 - [c56]Frantisek Grézl, Martin Karafiát
Semi-supervised bootstrapping approach for neural network feature extractor training. ASRU 2013: 470-475 - [c55]Ekaterina Egorova, Karel Veselý, Martin Karafiát
Manual and semi-automatic approaches to building a multilingual phoneme set. ICASSP 2013: 7324-7328 - [c54]Petr Motlícek
Feature and score level combination of subspace Gaussinas in LVCSR task. ICASSP 2013: 7604-7608 - [c53]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: 1228-1232 - [c52]Martin Karafiát, Frantisek Grézl, Mirko Hannemann, Karel Veselý, Jan Cernocký:
BUT BABEL system for spontaneous Cantonese. INTERSPEECH 2013: 2589-2593 - 2012
- [j3]Thomas Hain
Transcribing Meetings With the AMIDA Systems. IEEE Trans. Speech Audio Process. 20(2): 486-498 (2012) - [c51]Daniel Povey, Mirko Hannemann, Gilles Boulianne
Generating exact lattices in the WFST framework. ICASSP 2012: 4213-4216 - [c50]Sandro Cumani, Oldrich Plchot, Martin Karafiát
Independent component analysis and MLLR transforms for speaker identification. ICASSP 2012: 4365-4368 - [c49]Stefan Kombrink, Tomás Mikolov, Martin Karafiát
Improving language models for ASR using translated in-domain data. ICASSP 2012: 4405-4408 - [c48]Martin Karafiát
Region dependent linear transforms in multilingual speech recognition. ICASSP 2012: 4885-4888 - [c47]Shakti P. Rath, Martin Karafiát, Ondrej Glembek, Jan Cernocký:
A factorized representation of FMLLR transform based on QR-decomposition. INTERSPEECH 2012: 551-554 - [c46]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: 216-223 - [c45]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: 330-333 - [c44]Karel Veselý, Martin Karafiát
The language-independent bottleneck features. SLT 2012: 336-341 - [c43]Milos Janda, Martin Karafiát
Dealing with Numbers in Grapheme-Based Speech Recognition. TSD 2012: 438-445 - 2011
- [j2]Daniel Povey, Lukás Burget
The subspace Gaussian mixture model - A structured model for speech recognition. Comput. Speech Lang. 25(2): 404-439 (2011) - [c42]Karel Veselý, Martin Karafiát
Convolutive Bottleneck Network features for LVCSR. ASRU 2011: 42-47 - [c41]Martin Karafiát
iVector-based discriminative adaptation for automatic speech recognition. ASRU 2011: 152-157 - [c40]Frantisek Grézl, Martin Karafiát
Study of probabilistic and Bottle-Neck features in multilingual environment. ASRU 2011: 359-364 - [c39]Daniel Povey, Martin Karafiát
A symmetrization of the Subspace Gaussian Mixture Model. ICASSP 2011: 4504-4507 - [c38]Ondrej Glembek, Lukás Burget
Simplification and optimization of i-vector extraction. ICASSP 2011: 4516-4519 - [c37]Anoop Deoras, Tomás Mikolov, Stefan Kombrink, Martin Karafiát
Variational approximation of long-span language models for lvcsr. ICASSP 2011: 5532-5535 - [c36]Frantisek Grézl, Martin Karafiát:
Integrating Recent MLP Feature Extraction Techniques into TRAP Architecture. INTERSPEECH 2011: 1229-1232 - [c35]Stefan Kombrink, Tomás Mikolov, Martin Karafiát, Lukás Burget:
Recurrent Neural Network Based Language Modeling in Meeting Recognition. INTERSPEECH 2011: 2877-2880 - 2010
- [c34]Arnab Ghoshal, Daniel Povey, Mohit Agarwal, Pinar Akyazi, Lukás Burget
A novel estimation of feature-space MLLR for full-covariance models. ICASSP 2010: 4310-4313 - [c33]Daniel Povey, Lukás Burget
Subspace Gaussian Mixture Models for speech recognition. ICASSP 2010: 4330-4333 - [c32]Lukás Burget
Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models. ICASSP 2010: 4334-4337 - [c31]Nagendra Goel, Samuel Thomas, Mohit Agarwal, Pinar Akyazi, Lukás Burget
Approaches to automatic lexicon learning with limited training examples. ICASSP 2010: 5094-5097 - [c30]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: 5282-5285 - [c29]Thomas Hain
The AMIDA 2009 meeting transcription system. INTERSPEECH 2010: 358-361 - [c28]Mirko Hannemann, Stefan Kombrink, Martin Karafiát, Lukás Burget:
Similarity scoring for recognizing repeated out-of-vocabulary words. INTERSPEECH 2010: 897-900 - [c27]Tomás Mikolov, Martin Karafiát, Lukás Burget, Jan Cernocký, Sanjeev Khudanpur
Recurrent neural network based language model. INTERSPEECH 2010: 1045-1048 - [c26]Frantisek Grézl, Martin Karafiát:
Hierarchical neural net architectures for feature extraction in ASR. INTERSPEECH 2010: 1201-1204 - [c25]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: 37 - [c24]Martin Karafiát
Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data. TSD 2010: 322-329
2000 – 2009
- 2009
- [c23]Stefan Kombrink, Lukás Burget, Pavel Matejka, Martin Karafiát, Hynek Hermansky:
Posterior-based out of vocabulary word detection in telephone speech. INTERSPEECH 2009: 80-83 - [c22]Philip N. Garner, John Dines, Thomas Hain
Real-time ASR from meetings. INTERSPEECH 2009: 2119-2122 - [c21]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: 2335-2338 - [c20]Frantisek Grézl, Martin Karafiát, Lukás Burget:
Investigation into bottle-neck features for meeting speech recognition. INTERSPEECH 2009: 2947-2950 - 2008
- [c19]Martin Karafiát, Lukás Burget, Thomas Hain
Discrimininative training of narrow band - wide band adapted systems for meeting recognition. INTERSPEECH 2008: 1217-1220 - [c18]Jirí Kopecký, Ondrej Glembek, Martin Karafiát
Advances in Acoustic Modeling for the Recognition of Czech. TSD 2008: 357-363 - 2007
- [j1]Niko Brümmer, Lukás Burget
Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006. IEEE Trans. Speech Audio Process. 15(7): 2072-2084 (2007) - [c17]Thomas Hain
The 2007 AMI(DA) System for Meeting Transcription. CLEAR 2007: 414-428 - [c16]Pavel Matejka, Lukás Burget
STBU System for the NIST 2006 Speaker Recognition Evaluation. ICASSP (4) 2007: 221-224 - [c15]Thomas Hain
The AMI System for the Transcription of Speech in Meetings. ICASSP (4) 2007: 357-360 - [c14]Frantisek Grézl, Martin Karafiát
Probabilistic and Bottle-Neck Features for LVCSR of Meetings. ICASSP (4) 2007: 757-760 - [c13]Martin Karafiát, Lukás Burget, Jan Cernocký, Thomas Hain
Application of CMLLR in narrow band wide band adapted systems. INTERSPEECH 2007: 282-285 - [c12]Igor Szöke, Michal Fapso, Martin Karafiát
Spoken Term Detection System Based on Combination of LVCSR and Phonetic Search. MLMI 2007: 237-247 - 2006
- [c11]Michal Fapso, Pavel Smrz
Information Retrieval from Spoken Documents. CICLing 2006: 410-416 - [c10]Martin Karafiát
Robust Heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition. MLMI 2006: 275-284 - [c9]Thomas Hain
The AMI Meeting Transcription System: Progress and Performance. MLMI 2006: 419-431 - [c8]Lukás Burget
Indexing and Search Methods for Spoken Documents. TSD 2006: 351-358 - 2005
- [c7]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: 633-636 - [c6]Thomas Hain
Transcription of conference room meetings: an investigation. INTERSPEECH 2005: 1661-1664 - [c5]Thomas Hain
The Development of the AMI System for the Transcription of Speech in Meetings. MLMI 2005: 344-356 - [c4]Thomas Hain
The 2005 AMI System for the Transcription of Speech in Meetings. MLMI 2005: 450-462 - [c3]Igor Szöke, Petr Schwarz
Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech. TSD 2005: 302-309 - 2004
- [c2]Frantisek Grézl, Martin Karafiát, Jan Cernocký:
TRAP based features for LVCSR of meting data. INTERSPEECH 2004: 437-440 - 2002
- [c1]Pavel Matejka, Petr Schwarz
Some Like It Gaussian.... TSD 2002: 321-324
Coauthor Index
[c89] [c86] [c85] [i7] [i5] [c84] [c82] [c81] [c80] [i4] [i2] [c78] [c77] [c76] [p1] [c75] [c74] [c73] [c67] [c66] [c59] [c53] [j3] [c51] [c49] [c48] [j2] [c41] [c38] [c35] [c34] [c33] [c32] [c31] [c29] [c28] [c27] [c25] [c23] [c21] [c20] [c19] [j1] [c17] [c16] [c15] [c13] [c12] [c11] [c10] [c9] [c8] [c7] [c5] [c4] [c3]
[c89] [c88] [c87] [c86] [c85] [i8] [i7] [i6] [i5] [c84] [c83] [c82] [c81] [c80] [i4] [i2] [i1] [c78] [c77] [p1] [c75] [c74] [c73] [c70] [c67] [c66] [c65] [c61] [c59] [c55] [c53] [c52] [c48] [c47] [c46] [c45] [c43] [c41] [c27] [c25] [c24] [c21] [c19] [j1] [c16] [c14] [c13] [c12] [c11] [c10] [c8] [c7] [c3] [c2] [c1]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 22:07 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: