M. Karafiát

发表

Recurrent neural network based language model

Lukás Burget, Sanjeev Khudanpur, Jan Cernocký, 2010, INTERSPEECH.

The 2005 AMI System for the Transcription of Speech in Meetings

Lukás Burget, Roeland Ordelman, Thomas Hain, 2005, MLMI.

The AMI System for the Transcription of Speech in Meetings

Lukás Burget, Jithendra Vepa, Thomas Hain, 2007, ICASSP.

Probabilistic and Bottle-Neck Features for LVCSR of Meetings

Jan Cernocký, Martin Karafiát, Frantisek Grézl, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Recurrent Neural Network Based Language Modeling in Meeting Recognition

Lukás Burget, Martin Karafiát, Tomas Mikolov, 2011, INTERSPEECH.

The subspace Gaussian mixture model - A structured model for speech recognition

Kai Feng, Ariya Rastrow, Lukás Burget, 2011, Comput. Speech Lang..

Speaker vectors from subspace Gaussian mixture model as complementary features for language identification

Pavel Matejka, Jan Cernocký, Martin Karafiát, 2012, Odyssey.

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

Lukás Burget, Pavel Matejka, Jan Cernocký, 2007, MLMI.

SUBSPACE GAUSSIAN MIXTURE MODELS FOR SPEECH RECOGNITION

Kai Feng, Ariya Rastrow, Lukás Burget, 2009 .

Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Description and analysis of the Brno276 system for LRE2011

Pavel Matejka, Jan Cernocký, Sandro Cumani, 2012, Odyssey.

Some Like It Gaussian

Pavel Matejka, Jan Cernocký, Martin Karafiát, 2002, TSD.

Simplification and optimization of i-vector extraction

Lukás Burget, Pavel Matejka, Patrick Kenny, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

David A. van Leeuwen, Lukás Burget, Pavel Matejka, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system

Lukás Burget, Pavel Matejka, Jan Cernocký, 2010, Odyssey.

Region dependent linear transforms in multilingual speech recognition

Lukás Burget, Jan Cernocký, Martin Karafiát, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A novel estimation of feature-space MLLR for full-covariance models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Generating exact lattices in the WFST framework

Ngoc Thang Vu, Petr Motlícek, Lukás Burget, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The AMIDA 2009 meeting transcription system

Lukás Burget, Marijn Huijbregts, Thomas Hain, 2010, INTERSPEECH.

Comparison of keyword spotting approaches for informal continuous speech

Lukás Burget, Pavel Matejka, Jan Cernocký, 2005, INTERSPEECH.

Approaches to automatic lexicon learning with limited training examples

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

The AMI System for the Transcription of Speech in Meetings

Lukás Burget, Roeland Ordelman, Thomas Hain, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Spoken Language Technology for Under-resourced Languages , SLTU 2016 , 9-12 May 2016 , Yogyakarta , Indonesia BottleNeck Feature Extraction Structures for Multilingual Training and Porting

M. Karafiát, F. Grézl, 2016 .

Proceedings of the Rich Transcription 2005 Spring Meeting Recognition Evaluation

Roeland Ordelman, Thomas Hain, Steve Renals, 2005 .

Robust heteroscedastic linear discriminant analysis and LCRC posterior features in large vocabulary continuous speech recognition

Martin Karafiát, Petr Schwarz, Lukáš Burget, 2022 .

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

Roeland Ordelman, Thomas Hain, Steve Renals, 2003 .

Score normalization and system combination for improved keyword spotting

Richard M. Schwartz, John Makhoul, Le Zhang, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Independent component analysis and MLLR transforms for speaker identification

Sandro Cumani, Martin Karafiát, Oldrich Plchot, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transcription of conference room meetings: an investigation

Roeland Ordelman, Thomas Hain, Martin Karafiát, 2005, INTERSPEECH.

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

Martin Karafiát, Frantisek Grézl, Karel Veselý, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling

Shinji Watanabe, Sri Harish Reddy Mallidi, Takaaki Hori, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

BUT System for Low Resource Indian Language ASR

Lukás Burget, Jan Cernocký, Martin Karafiát, 2018, INTERSPEECH.

Analysis of Multilingual Sequence-to-Sequence speech recognition systems

Shinji Watanabe, Takaaki Hori, Martin Karafiát, 2018, INTERSPEECH.

Jointly Trained Transformers Models for Spoken Language Translation pdf

Jan Cernocký, Katerina Zmolíková, Martin Karafiát, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Martin Karafiát, Frantisek Grézl, M. Karafiát, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

BUT Zero-Cost Speech Recognition 2016 System Description

Martin Karafiát, Igor Szöke, Lucas Ondel, 2016, MediaEval.

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

Lukas Burget, Jan Cernocky, Martin Karafiat, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Real-time ASR from meetings

Le Zhang, Thomas Hain, Martin Karafiát, 2009, INTERSPEECH.

Lukás Burget, Martin Karafiát, Mirko Hannemann, 2010, INTERSPEECH.

But ASR system for BABEL Surprise evaluation 2014

Lukás Burget, Jan Cernocký, Martin Karafiát, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Analysis of X-Vectors for Low-Resource Speech Recognition

Martin Karafiát, Karel Veselý, Jan Profant, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Robust speech recognition in unknown reverberant and noisy conditions

Hynek Hermansky, Shinji Watanabe, Richard M. Schwartz, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

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

Martin Karafiát, Frantisek Grézl, M. Karafiát, 2014, INTERSPEECH.

Training Data Augmentation and Data Selection

Shinji Watanabe, Marc Delcroix, Lukás Burget, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

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

Lukás Burget, Jan Cernocký, Martin Karafiát, 2015, INTERSPEECH.

The AMI Meeting Transcription System: Progress and Performance

Lukás Burget, Jithendra Vepa, Thomas Hain, 2006, MLMI.

Promising Accurate Prefix Boosting for Sequence-to-sequence ASR

Shinji Watanabe, Lukás Burget, Takaaki Hori, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech

Lukás Burget, Pavel Matejka, Jan Cernocký, 2005, TSD.

Subspace Gaussian Mixture Models for speech recognition

M. Karafiát, L. Burget, Daniel Povey, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.