Institution
Brno University of Technology
Education•Brno, Czechia•
About: Brno University of Technology is a education organization based out in Brno, Czechia. It is known for research contribution in the topics: Fracture mechanics & Filter (video). The organization has 6339 authors who have published 15226 publications receiving 194088 citations. The organization is also known as: Vysoké učení technické v Brně & BUT.
Papers published on a yearly basis
Papers
More filters
•
TL;DR: This paper proposed two novel model architectures for computing continuous vector representations of words from very large data sets, and the quality of these representations is measured in a word similarity task and the results are compared to the previously best performing techniques based on different types of neural networks.
Abstract: We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Furthermore, we show that these vectors provide state-of-the-art performance on our test set for measuring syntactic and semantic word similarities.
20,077 citations
•
16 Jan 2013TL;DR: Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
Abstract: We propose two novel model architectures for computing continuous vector
representations of words from very large data sets. The quality of these
representations is measured in a word similarity task, and the results are
compared to the previously best performing techniques based on different types
of neural networks. We observe large improvements in accuracy at much lower
computational cost, i.e. it takes less than a day to learn high quality word
vectors from a 1.6 billion words data set. Furthermore, we show that these
vectors provide state-of-the-art performance on our test set for measuring
syntactic and semantic word similarities.
9,270 citations
•
01 Jan 2011
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.
Abstract: We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state automata (using the freely available OpenFst), together with detailed documentation and a comprehensive set of scripts for building complete recognition systems. Kaldi is written is C++, and the core library supports modeling of arbitrary phonetic-context sizes, acoustic modeling with subspace Gaussian mixture models (SGMM) as well as standard Gaussian mixture models, together with all commonly used linear and affine transforms. Kaldi is released under the Apache License v2.0, which is highly nonrestrictive, making it suitable for a wide community of users.
5,857 citations
•
01 Jan 2010TL;DR: Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.
Abstract: A new recurrent neural network based language model (RNN LM) with applications to speech recognition is presented. Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model. Speech recognition experiments show around 18% reduction of word error rate on the Wall Street Journal task when comparing models trained on the same amount of data, and around 5% on the much harder NIST RT05 task, even when the backoff model is trained on much more data than the RNN LM. We provide ample empirical evidence to suggest that connectionist language models are superior to standard n-gram techniques, except their high computational (training) complexity. Index Terms: language modeling, recurrent neural networks, speech recognition
5,751 citations
•
TL;DR: This paper proposes a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem and validates empirically the hypothesis and proposed solutions.
Abstract: There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying issues by exploring these problems from an analytical, a geometric and a dynamical systems perspective. Our analysis is used to justify a simple yet effective solution. We propose a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section.
3,549 citations
Authors
Showing all 6383 results
Name | H-index | Papers | Citations |
---|---|---|---|
Georg Kresse | 111 | 430 | 244729 |
Patrik Schmuki | 109 | 763 | 52669 |
Michael Schmid | 88 | 715 | 30874 |
Robert M. Malina | 88 | 691 | 38277 |
Jiří Jaromír Klemeš | 64 | 565 | 14892 |
Alessandro Piccolo | 62 | 284 | 14332 |
René Kizek | 61 | 672 | 16554 |
George Danezis | 59 | 209 | 11516 |
Stevo Stević | 58 | 374 | 9832 |
Edvin Lundgren | 57 | 286 | 10158 |
Franz Halberg | 55 | 750 | 15400 |
Vojtech Adam | 55 | 611 | 14442 |
Lukas Burget | 53 | 252 | 21375 |
Jan Cermak | 53 | 238 | 9563 |
Hynek Hermansky | 51 | 317 | 14372 |