K
Karel Vesely
Researcher at Brno University of Technology
Publications - 23
Citations - 6839
Karel Vesely is an academic researcher from Brno University of Technology. The author has contributed to research in topics: Artificial neural network & Engineering. The author has an hindex of 12, co-authored 20 publications receiving 6098 citations.
Papers
More filters
Proceedings Article
The Kaldi Speech Recognition Toolkit
Daniel Povey,Arnab Ghoshal,Gilles Boulianne,Lukas Burget,Ondrej Glembek,Nagendra Kumar Goel,Mirko Hannemann,Petr Motlicek,Yanmin Qian,Petr Schwarz,Jan Silovsky,Georg Stemmer,Karel Vesely +12 more
TL;DR: The design of Kaldi is described, a free, open-source toolkit for speech recognition research that provides a speech recognition system based on finite-state automata together with detailed documentation and a comprehensive set of scripts for building complete recognition systems.
Proceedings ArticleDOI
The language-independent bottleneck features
TL;DR: This paper presents novel language-independent bottleneck (BN) feature extraction framework, where each language is modelled by separate output layer, while all the hidden layers jointly model the variability of all the source languages.
Proceedings ArticleDOI
Semi-supervised training of Deep Neural Networks
TL;DR: It is beneficial to reduce the disproportion in amounts of transcribed and untranscribed data by including the transcribed data several times, as well as to do a frame-selection based on per-frame confidences derived from confusion in a lattice.
Proceedings ArticleDOI
Generating exact lattices in the WFST framework
Daniel Povey,Mirko Hannemann,Gilles Boulianne,Lukas Burget,Arnab Ghoshal,Milos Janda,Martin Karafiat,Stefan Kombrink,Petr Motlicek,Yanmin Qian,Korbinian Riedhammer,Karel Vesely,Ngoc Thang Vu +12 more
TL;DR: A lattice generation method that is exact, i.e. it satisfies all the natural properties the authors would want from a lattice of alternative transcriptions of an utterance, and does not introduce substantial overhead above one-best decoding.
Proceedings ArticleDOI
Convolutive Bottleneck Network features for LVCSR
TL;DR: A Convolutive Bottleneck Network is proposed as extension of the current state-of-the-art Universal Context Network and leads to 5.5% relative reduction of WER, compared to the Universal Context ANN baseline.