J
Jan Cernocky
Researcher at Brno University of Technology
Publications - 80
Citations - 5742
Jan Cernocky is an academic researcher from Brno University of Technology. The author has contributed to research in topics: Speaker recognition & NIST. The author has an hindex of 26, co-authored 80 publications receiving 5158 citations.
Papers
More filters
Proceedings ArticleDOI
Extensions of recurrent neural network language model
TL;DR: Several modifications of the original recurrent neural network language model are presented, showing approaches that lead to more than 15 times speedup for both training and testing phases and possibilities how to reduce the amount of parameters in the model.
Proceedings ArticleDOI
Strategies for training large scale neural network language models
TL;DR: This work describes how to effectively train neural network based language models on large data sets and introduces hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model.
Proceedings ArticleDOI
Probabilistic and Bottle-Neck Features for LVCSR of Meetings
TL;DR: This work is exploring the possibility of obtaining the features directly from neural net without the necessity of converting output probabilities to features suitable for subsequent GMM-HMM system.
RNNLM - Recurrent Neural Network Language Modeling Toolkit
TL;DR: A freely available open-source toolkit for training recurrent neural network based language models that can be easily used to improve existing speech recognition and machine translation systems and used as a baseline for future research of advanced language modeling techniques.
Journal ArticleDOI
Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006
Niko Brümmer,Lukas Burget,Jan Cernocky,Ondrej Glembek,Frantisek Grezl,Martin Karafiat,D.A. van Leeuwen,Pavel Matejka,Petr Schwarz,Albert Strasheim +9 more
TL;DR: The STBU speaker recognition system was a combination of three main kinds of subsystems, which performed well in the NIST Speaker Recognition Evaluation 2006 (SRE).