Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Karafiat, Martin"'
Autor:
Karafiát, Martin, Veselý, Karel, Szöke, Igor, Mošner, Ladislav, Beneš, Karel, Witkowski, Marcin, Barchi, Germán, Pepino, Leonardo
This paper describes the joint effort of Brno University of Technology (BUT), AGH University of Krakow and University of Buenos Aires on the development of Automatic Speech Recognition systems for the CHiME-7 Challenge. We train and evaluate various
Externí odkaz:
http://arxiv.org/abs/2310.11921
Autor:
Kocour, Martin, Cámbara, Guillermo, Luque, Jordi, Bonet, David, Farrús, Mireia, Karafiát, Martin, Veselý, Karel, Ĉernocký, Jan ''Honza''
This paper describes joint effort of BUT and Telef\'onica Research on development of Automatic Speech Recognition systems for Albayzin 2020 Challenge. We compare approaches based on either hybrid or end-to-end models. In hybrid modelling, we explore
Externí odkaz:
http://arxiv.org/abs/2101.12729
Autor:
Karafiát, Martin, Baskar, Murali Karthick, Szöke, Igor, Vydana, Hari Krishna, Veselý, Karel, Černocký, Jan "Honza''
The paper describes the BUT Automatic Speech Recognition (ASR) systems submitted for OpenSAT evaluations under two domain categories such as low resourced languages and public safety communications. The first was challenging due to lack of training d
Externí odkaz:
http://arxiv.org/abs/2001.11360
Autor:
Karafiát, Martin, Baskar, Murali Karthick, Watanabe, Shinji, Hori, Takaaki, Wiesner, Matthew, Černocký, Jan "Honza''
This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set composed of Babel data, we first sh
Externí odkaz:
http://arxiv.org/abs/1811.03451
Autor:
Baskar, Murali Karthick, Burget, Lukáš, Watanabe, Shinji, Karafiát, Martin, Hori, Takaaki, Černocký, Jan Honza
In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme in an effective manner. The trai
Externí odkaz:
http://arxiv.org/abs/1811.02770
Autor:
Cho, Jaejin, Baskar, Murali Karthick, Li, Ruizhi, Wiesner, Matthew, Mallidi, Sri Harish, Yalta, Nelson, Karafiat, Martin, Watanabe, Shinji, Hori, Takaaki
Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of requiring mor
Externí odkaz:
http://arxiv.org/abs/1810.03459
Autor:
Baskar, Murali Karthick, Karafiat, Martin, Burget, Lukas, Vesely, Karel, Grezl, Frantisek, Cernocky, Jan Honza
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simpl
Externí odkaz:
http://arxiv.org/abs/1808.01916
Autor:
Grézl, František, Karafiát, Martin
Publikováno v:
In Procedia Computer Science 2016 81:144-151
Publikováno v:
In Procedia Computer Science 2016 81:15-22
Autor:
Povey, Daniel, Burget, Lukáš, Agarwal, Mohit, Akyazi, Pinar, Kai, Feng, Ghoshal, Arnab, Glembek, Ondřej, Goel, Nagendra, Karafiát, Martin, Rastrow, Ariya, Rose, Richard C., Schwarz, Petr, Thomas, Samuel
Publikováno v:
In Computer Speech & Language 2011 25(2):404-439