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: The behavior of surface texturing based on shallow micro-dents was observed within mixed lubricated non-conformal contacts and compared with results obtained under thin film elastohydrodynamic conditions as discussed by the authors.
61 citations
••
30 Apr 2019TL;DR: This work proposes a new semi-supervised loss combining an end-to-end differentiable ASR loss that is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of \%WER.
Abstract: Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such models. This work builds upon recent results showing notable improvements in semi-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models. In particular, this work proposes a new semi-supervised loss combining an end-to-end differentiable ASR$\rightarrow$TTS loss with TTS$\rightarrow$ASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of \%WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided in ESPnet to reproduce the experiments.
61 citations
••
TL;DR: The dynamic behavior analysis presented here proves that the introduction of an energy storage element into the EGS with variable-engine-speed concept eliminates this drawback.
Abstract: Current development trends regarding mobile electrical-generator sets (EGSs) indicate that enhancement of efficiency is to be sought in means to operate the driving engine (either diesel or gasoline) continuously at its optimum speed. The engine-generator dynamics at a sudden load change (from low load to high load) remains a challenge in this regard. The dynamic behavior analysis presented here proves that the introduction of an energy storage element into the EGS with variable-engine-speed concept eliminates this drawback. This paper addresses the identification of the dynamic behavior of such variable-speed EGS systems and the problems encountered during a sudden increase of load (power and voltage drops).
61 citations
••
TL;DR: This study proposes a current mode canonical single resistance-controlled oscillator (SRCO) circuit based on a single modified current differencing transconductance amplifier that enables orthogonal control of frequency and oscillation condition.
Abstract: This study proposes a current mode canonical single resistance-controlled oscillator (SRCO) circuit based on a single modified current differencing transconductance amplifier. The circuit employs grounded capacitors and provides a current output with high output impedance. The proposed circuit also enables orthogonal control of frequency and oscillation condition. The performance of the proposed SRCO is verified by means of simulation program with integrated circuit emphasis (SPICE) simulations, on-chip experiments and measurements.
61 citations
••
04 May 2014TL;DR: A technique of Within-Class Covariance Correction (WCC) for Linear Discriminant Analysis (LDA) in Speaker Recognition is proposed to perform an unsupervised adaptation of LDA to an unseen data domain, and/or to compensate for speaker population difference among different portions of L DA training dataset.
Abstract: In this paper we propose a technique of Within-Class Covariance Correction (WCC) for Linear Discriminant Analysis (LDA) in Speaker Recognition to perform an unsupervised adaptation of LDA to an unseen data domain, and/or to compensate for speaker population difference among different portions of LDA training dataset. The paper follows on the study of source-normalization and inter-database variability compensation techniques which deal with multimodal distribution of i-vectors. On the DARPA RATS (Robust Automatic Transcription of Speech) task, we show that, with two hours of unsupervised data, we improve the Equal-Error Rate (EER) by 17.5%, and 36% relative on the unmatched and semi-matched conditions, respectively. On the Domain Adaptation Challenge we show up to 70% relative EER reduction and we propose a data clustering procedure to identify the directions of the domain-based variability in the adaptation data.
61 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 |