Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Karel Vesely"'
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
Publikováno v:
Interspeech 2021
We launched a community platform for collecting the ATC speech world-wide in the ATCO2 project. Filtering out unseen non-English speech is one of the main components in the data processing pipeline. The proposed English Language Detection (ELD) syste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::600da203fac1e06cfb2298c9aba2bac5
http://arxiv.org/abs/2104.02332
http://arxiv.org/abs/2104.02332
Autor:
Martin Karafidt, Karel Vesely, Lukas Burget, Frantisek Grezl, Jan Cernocky, Murali Karthick Baskar
Publikováno v:
ICASSP
The paper provides an analysis of automatic speech recognition systems (ASR) based on multilingual BLSTM, where we used multi-task training with separate classification layer for each language. The focus is on low resource languages, where only a lim
Autor:
Murali Karthick Baskar, Frantisek Grezl, Jan Cernocky, Karel Vesely, Pavel Matejka, Martin Karafiat
Publikováno v:
SLT
This paper provides an extensive summary of BUT 2016 system for the last IARPA Babel evaluations. It concentrates on multi-lingual training of both deep neural network (DNN)-based feature extraction and acoustic models including multilingual training
Autor:
Lenka Fajkusová, Karel Vesely, Hana Ošlejšková, Hana Bučková, Lenka Kopečková, Markéta Hermanová, Lenka Mrázová, Jana Kyrova
Publikováno v:
Journal of dermatological case reports. 10(3)
Background: Epidermolysis bullosa simplex associated with muscular dystrophy is a genetic skin disease caused by plectin deficiency. A case of a 19-year-old Czech patient affected with this disease and a review all previously published clinical cases
Publikováno v:
ICASSP
In recent years, trained feature extraction (FE) schemes based on neural networks have replaced or complemented traditional approaches in top performing systems. This paper deals with FE in multilingual scenarios with a target language with low amoun
Autor:
Hana Bučková, Marketa Vlckova, Anna Sediva, Barbora Ravčuková, Zdenek Sedlacek, Ester Mejstrikova, Edita Kabickova, David Sumerauer, Jan Stary, Miroslava Hancarova, Ales Janda, Ondrej Hrusak, Tomáš Freiberger, Lenka Kopečková, Karel Vesely, Lenka Fajkusová
Publikováno v:
Pediatrics. 129:e523-e528
SH2D1A gene defects are the cause of X-linked lymphoproliferative disorder (XLP-1), a rare condition characterized by severe immune dysregulation. We present a patient lacking the typical symptoms of XLP-1, but experiencing a severe unusual skin cond
Autor:
Richard M. Stern, Matthew Wiesner, Anjali Menon, Vijayaditya Peddinti, John J. Godfrey, Richard Rose, Sri Harish Mallidi, Hynek Hermansky, Karel Vesely, Jordan Cohen, Emmanuel Dupoux, Sanjeev Khudanpur, Lukas Burget, Tetsuji Ogawa, Matthew Maciejewski, Naomi H. Feldman
Publikováno v:
ICASSP
A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a dif
Autor:
Frantisek Grezl, Karel Vesely, Mirko Hannemann, Igor Szöke, Jan Cernocky, Lukas Burget, Martin Karafiat
Publikováno v:
SLT
The paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil). While being largely based on our previous work, two original contributions were brought: (1) speaker-adapted bottle-neck neural ne
Publikováno v:
ICASSP
The neural network based features became an inseparable part of state-of-the-art LVCSR systems. In order to perform well, the network has to be trained on a large amount of in-domain data. With the increasing emphasis on fast development of ASR syste