Brno University of Technology

research

∙ 04/29/2022

Lipschitz-based Surrogate Model for High-dimensional Computationally Expensive Problems

Standard evolutionary optimization algorithms assume that the evaluation...

Jakub Kúdela, et al. ∙

research

∙ 01/05/2019

Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning

For real-world speech recognition applications, noise robustness is stil...

Ladislav Mošner, et al. ∙

research

∙ 04/06/2019

Self-supervised speaker embeddings

Contrary to i-vectors, speaker embeddings such as x-vectors are incapabl...

Themos Stafylakis, et al. ∙

research

∙ 07/02/2019

Brno Mobile OCR Dataset

We introduce the Brno Mobile OCR Dataset (B-MOD) for document Optical Ch...

Martin Kišš, et al. ∙

research

∙ 02/21/2017

Traffic Surveillance Camera Calibration by 3D Model Bounding Box Alignment for Accurate Vehicle Speed Measurement

In this paper, we focus on fully automatic traffic surveillance camera c...

Jakub Sochor, et al. ∙

research

∙ 08/24/2016

Absolute Pose Estimation from Line Correspondences using Direct Linear Transformation

This work is concerned with camera pose estimation from correspondences ...

Bronislav Přibyl, et al. ∙

research

∙ 02/25/2016

CNN for License Plate Motion Deblurring

In this work we explore the previously proposed approach of direct blind...

Pavel Svoboda, et al. ∙

research

∙ 02/10/2016

Gabor Wavelets in Image Processing

This work shows the use of a two-dimensional Gabor wavelets in image pro...

David Barina, et al. ∙

research

∙ 06/12/2015

Technical Report: Image Captioning with Semantically Similar Images

This report presents our submission to the MS COCO Captioning Challenge ...

Martin Kolář, et al. ∙

research

∙ 05/09/2017

New Transforms for JPEG Format

The two-dimensional discrete cosine transform (DCT) can be found in the ...

Stanislav Svoboda, et al. ∙

research

∙ 09/25/2017

Simple Signal Extension Method for Discrete Wavelet Transform

Discrete wavelet transform of finite-length signals must necessarily han...

David Barina, et al. ∙

research

∙ 10/06/2017

End-to-end DNN Based Speaker Recognition Inspired by i-vector and PLDA

Recently several end-to-end speaker verification systems based on deep n...

Johan Rohdin, et al. ∙

research

∙ 12/15/2016

HADES: Microprocessor Hazard Analysis via Formal Verification of Parameterized Systems

HADES is a fully automated verification tool for pipeline-based micropro...

Lukáš Charvát, et al. ∙

research

∙ 02/27/2018

Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model

Embeddings in machine learning are low-dimensional representations of co...

Niko Brümmer, et al. ∙

research

∙ 03/06/2018

Automation of Processor Verification Using Recurrent Neural Networks

When considering simulation-based verification of processors, the curren...

Martin Fajcik, et al. ∙

research

∙ 05/07/2018

Improving Network Intrusion Detection Classifiers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial Approach

Machine-learning based intrusion detection classifiers are able to detec...

Ivan Homoliak, et al. ∙

research

∙ 05/21/2018

Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

Horizon or skyline detection plays a vital role towards mountainous visu...

Touqeer Ahmad, et al. ∙

research

∙ 08/06/2018

Residual Memory Networks: Feed-forward approach to learn long temporal dependencies

Training deep recurrent neural network (RNN) architectures is complicate...

Murali Karthick Baskar, et al. ∙

research

∙ 09/28/2018

Spoken Pass-Phrase Verification in the i-vector Space

The task of spoken pass-phrase verification is to decide whether a test ...

Hossein Zeinali, et al. ∙

research

∙ 10/04/2018

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...

Jaejin Cho, et al. ∙

research

∙ 10/31/2018

Discriminatively Re-trained i-vector Extractor for Speaker Recognition

In this work we revisit discriminative training of the i-vector extracto...

Ondrej Novotny, et al. ∙

research

∙ 10/31/2018

Introducing SPAIN (SParse Audion INpainter)

A novel sparsity-based algorithm for audio inpainting is proposed by tra...

Ondřej Mokrý, et al. ∙

research

∙ 11/06/2018

Language model integration based on memory control for sequence to sequence speech recognition

In this paper, we explore several new schemes to train a seq2seq model t...

Jaejin Cho, et al. ∙

research

∙ 11/07/2018

Promising Accurate Prefix Boosting for sequence-to-sequence ASR

In this paper, we present promising accurate prefix boosting (PAPB), a d...

Murali Karthick Baskar, et al. ∙

research

∙ 11/07/2018

On the use of DNN Autoencoder for Robust Speaker Recognition

In this paper, we present an analysis of a DNN-based autoencoder for spe...

Ondrej Novotny, et al. ∙

research

∙ 11/06/2018

Speaker verification using end-to-end adversarial language adaptation

In this paper we investigate the use of adversarial domain adaptation fo...

Johan Rohdin, et al. ∙

research

∙ 11/19/2018

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

In this work, we present an analysis of a DNN-based autoencoder for spee...

Ondrej Novotny, et al. ∙

research

∙ 12/06/2018

Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss

This paper deals with segmentation of organs at risk (OAR) in head and n...

Oldřich Kodym, et al. ∙

research

∙ 02/25/2019

BUT-FIT at SemEval-2019 Task 7: Determining the Rumour Stance with Pre-Trained Deep Bidirectional Transformers

This paper describes our system submitted to SemEval 2019 Task 7: Rumour...

Martin Fajcik, et al. ∙

research

∙ 02/22/2019

autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components

Approximate computing is an emerging paradigm for developing highly ener...

Vojtech Mrazek, et al. ∙

research

∙ 03/11/2019

Automated Circuit Approximation Method Driven by Data Distribution

We propose an application-tailored data-driven fully automated method fo...

Zdenek Vasicek, et al. ∙

research

∙ 03/12/2019

Learning Feature Aggregation in Temporal Domain for Re-Identification

Person re-identification is a standard and established problem in the co...

Jakub Špaňhel, et al. ∙

research

∙ 04/08/2019

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

This work tackles the problem of learning a set of language specific aco...

Lucas Ondel, et al. ∙

research

∙ 04/05/2019

Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition

In this work, we continue in our research on i-vector extractor for spea...

Ondrej Novotny, et al. ∙

research

∙ 04/30/2019

Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

Sequence-to-sequence ASR models require large quantities of data to atta...

Murali Karthick Baskar, et al. ∙

research

∙ 05/17/2019

Simulations in Rank-Based Büchi Automata Complementation

The long search for an optimal complementation construction for Büchi au...

Yu-Fang Chen, et al. ∙

research

∙ 07/13/2019

Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors

In this paper, we combine Hidden Markov Models (HMMs) with i-vector extr...

Nooshin Maghsoodi, et al. ∙

research

∙ 06/11/2019

ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining

The state-of-the-art approaches employ approximate computing to improve ...

Vojtech Mrazek, et al. ∙

research

∙ 07/13/2019

Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge

In this paper, we present the system description of the joint efforts of...

Hossein Zeinali, et al. ∙

research

∙ 08/20/2019

Learning document embeddings along with their uncertainties

Majority of the text modelling techniques yield only point estimates of ...

Santosh Kesiraju, et al. ∙

research

∙ 09/15/2019

Brno Urban Dataset -- The New Data for Self-Driving Agents and Mapping Tasks

Autonomous driving is a dynamically growing field of research, where qua...

Adam Ligocki, et al. ∙

research

∙ 11/20/2019

Segmentation of Defective Skulls from CT Data for Tissue Modelling

In this work we present a method of automatic segmentation of defective ...

Oldřich Kodym, et al. ∙

research

∙ 12/02/2019

ReD-CaNe: A Systematic Methodology for Resilience Analysis and Design of Capsule Networks under Approximations

Recent advances in Capsule Networks (CapsNets) have shown their superior...

Alberto Marchisio, et al. ∙

research

∙ 01/08/2020

Audio Inpainting: Revisited and Reweighted

We deal with the problem of sparsity-based audio inpainting. A consequen...

Ondřej Mokrý, et al. ∙

research

∙ 02/21/2020

TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU

Energy efficiency of hardware accelerators of deep neural networks (DNN)...

Filip Vaverka, et al. ∙

research

∙ 04/22/2020

Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks

Approximate circuits have been developed to provide good tradeoffs betwe...

Vojtech Mrazek, et al. ∙

research

∙ 04/22/2020

ApproxFPGAs: Embracing ASIC-Based Approximate Arithmetic Components for FPGA-Based Systems

There has been abundant research on the development of Approximate Circu...

Bharath Srinivas Prabakaran, et al. ∙

research

∙ 04/23/2020

Semantically-Oriented Mutation Operator in Cartesian Genetic Programming for Evolutionary Circuit Design

Despite many successful applications, Cartesian Genetic Programming (CGP...

David Hodan, et al. ∙

research

∙ 04/25/2020

Jointly Trained Transformers models for Spoken Language Translation

Conventional spoken language translation (SLT) systems are pipeline base...

Hari Krishna Vydana, et al. ∙

research

∙ 06/17/2020

Multi-Agent Programming Contest 2019 FIT BUT Team solution

During our participation in MAPC 2019, we have developed two multi-agent...

Vaclav Uhlir, et al. ∙

Brno University of Technology

Featured Researchers