Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Martin Karafiat"'
Autor:
Martin Kocour, Jahnavi Umesh, Martin Karafiat, Ján Švec, Fernando López, Jordi Luque, Karel Beneš, Mireia Diez, Igor Szoke, Karel Veselý, Lukáš Burget, Jan Černocký
Publikováno v:
IberSPEECH 2022.
Autor:
Jan Profant, Jiri Nytra, Martin Karafiat, Jan Cernocky, Tomas Pavlicek, Miroslav Hlavacek, Karel Vesely
Publikováno v:
ICASSP
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
The paper presents a study of usability of x-vectors for adaptation of automatic speech recognition (ASR) systems. X-vectors are Neural Network (NN)-based speaker embeddings recently proposed in speaker recognition (SR). They quickly replaced common
Autor:
David Bonet, Jordi Luque, Martin Kocour, Guillermo Cámbara, Mireia Farrús, Karel Veselý, Martin Karafiat, Jan Cernocký
Publikováno v:
IberSPEECH 2021, Proceedings-ISCA 2021
IberSPEECH 2021
IberSPEECH
IberSPEECH 2021
IberSPEECH
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbc5ba549fb9429d0e12f6d1545366b7
http://arxiv.org/abs/2101.12729
http://arxiv.org/abs/2101.12729
Publikováno v:
IWSLT
The paper describes BUT’s English to German offline speech translation (ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on MustC-Common
Publikováno v:
ICASSP
Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to translate so
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73bb10cb8a719b0bfde5fb88213a4fde
http://arxiv.org/abs/2004.12111
http://arxiv.org/abs/2004.12111
Publikováno v:
SLTU
Procedia Computer Science
Procedia Computer Science
This study investigates the behavior of a feature extraction neural network model trained on a large amount of single language data (“source language”) on a set of under-resourced target languages. The coverage of the source language acoustic spa
Autor:
Bhargav Pulugundla, Jan Cernocký, Santosh Kesiraju, Murali Karthick Baskar, Ekaterina Egorova, Lukas Burget, Martin Karafiat
Publikováno v:
INTERSPEECH
Autor:
Frantisek Grezl, Jan Cernocký, Murali Karthick Baskar, Martin Karafiat, Igor Szöke, Karel Veselý, Vladimir Malenovský, Lukas Burget
Publikováno v:
INTERSPEECH
Autor:
Murali Karthick Baskar, Takaaki Hori, Martin Karafiat, Lukas Burget, Shinji Watanabe, Jan Cernocky
Publikováno v:
ICASSP
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0cd2da8e0b0dbbde1f240be4d076c43c
Autor:
Matthew Wiesner, Martin Karafiat, Nelson Yalta, Shinji Watanabe, Takaaki Hori, Sri Harish Mallidi, Murali Karthick Baskar, Ruizhi Li, Jaejin Cho
Publikováno v:
SLT
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3f69fc4fd11875ffbe485744ed625fb2