Brno University of Technology

∙ Brno , Czech Republic ∙ 0 followers

Brno University of Technology is a Czech university with more than one hundred years of tradition. Brno University of Technology ranks among three percent of the world's best universities and is constantly strengthening its position as a leading scientific and research institution. At eight faculties and two high...

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

For real-world speech recognition applications, noise robustness is stil...
01/05/2019 ∙ by Ladislav Mošner, et al. ∙ 6 ∙ share

read it
Self-supervised speaker embeddings

Contrary to i-vectors, speaker embeddings such as x-vectors are incapabl...
04/06/2019 ∙ by Themos Stafylakis, et al. ∙ 2 ∙ share

read it
Brno Mobile OCR Dataset

We introduce the Brno Mobile OCR Dataset (B-MOD) for document Optical Ch...
07/02/2019 ∙ by Martin Kišš, et al. ∙ 2 ∙ share

read it
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...
02/21/2017 ∙ by Jakub Sochor, et al. ∙ 0 ∙ share

read it
Absolute Pose Estimation from Line Correspondences using Direct Linear Transformation

This work is concerned with camera pose estimation from correspondences ...
08/24/2016 ∙ by Bronislav Přibyl, et al. ∙ 0 ∙ share

read it
CNN for License Plate Motion Deblurring

In this work we explore the previously proposed approach of direct blind...
02/25/2016 ∙ by Pavel Svoboda, et al. ∙ 0 ∙ share

read it
Gabor Wavelets in Image Processing

This work shows the use of a two-dimensional Gabor wavelets in image pro...
02/10/2016 ∙ by David Barina, et al. ∙ 0 ∙ share

read it
Technical Report: Image Captioning with Semantically Similar Images

This report presents our submission to the MS COCO Captioning Challenge ...
06/12/2015 ∙ by Martin Kolář, et al. ∙ 0 ∙ share

read it
New Transforms for JPEG Format

The two-dimensional discrete cosine transform (DCT) can be found in the ...
05/09/2017 ∙ by Stanislav Svoboda, et al. ∙ 0 ∙ share

read it
Simple Signal Extension Method for Discrete Wavelet Transform

Discrete wavelet transform of finite-length signals must necessarily han...
09/25/2017 ∙ by David Barina, et al. ∙ 0 ∙ share

read it
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...
10/06/2017 ∙ by Johan Rohdin, et al. ∙ 0 ∙ share

read it
HADES: Microprocessor Hazard Analysis via Formal Verification of Parameterized Systems

HADES is a fully automated verification tool for pipeline-based micropro...
12/15/2016 ∙ by Lukáš Charvát, et al. ∙ 0 ∙ share

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

Embeddings in machine learning are low-dimensional representations of co...
02/27/2018 ∙ by Niko Brümmer, et al. ∙ 0 ∙ share

read it
Automation of Processor Verification Using Recurrent Neural Networks

When considering simulation-based verification of processors, the curren...
03/06/2018 ∙ by Martin Fajcik, et al. ∙ 0 ∙ share

read it
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...
05/07/2018 ∙ by Ivan Homoliak, et al. ∙ 0 ∙ share

read it
Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

Horizon or skyline detection plays a vital role towards mountainous visu...
05/21/2018 ∙ by Touqeer Ahmad, et al. ∙ 0 ∙ share

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

Training deep recurrent neural network (RNN) architectures is complicate...
08/06/2018 ∙ by Murali Karthick Baskar, et al. ∙ 0 ∙ share

read it
Spoken Pass-Phrase Verification in the i-vector Space

The task of spoken pass-phrase verification is to decide whether a test ...
09/28/2018 ∙ by Hossein Zeinali, et al. ∙ 0 ∙ share

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

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...
10/04/2018 ∙ by Jaejin Cho, et al. ∙ 0 ∙ share

read it
Discriminatively Re-trained i-vector Extractor for Speaker Recognition

In this work we revisit discriminative training of the i-vector extracto...
10/31/2018 ∙ by Ondrej Novotny, et al. ∙ 0 ∙ share

read it
Introducing SPAIN (SParse Audion INpainter)

A novel sparsity-based algorithm for audio inpainting is proposed by tra...
10/31/2018 ∙ by Ondřej Mokrý, et al. ∙ 0 ∙ share

read it
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...
11/06/2018 ∙ by Jaejin Cho, et al. ∙ 0 ∙ share

read it
Promising Accurate Prefix Boosting for sequence-to-sequence ASR

In this paper, we present promising accurate prefix boosting (PAPB), a d...
11/07/2018 ∙ by Murali Karthick Baskar, et al. ∙ 0 ∙ share

read it
On the use of DNN Autoencoder for Robust Speaker Recognition

In this paper, we present an analysis of a DNN-based autoencoder for spe...
11/07/2018 ∙ by Ondrej Novotny, et al. ∙ 0 ∙ share

read it
Speaker verification using end-to-end adversarial language adaptation

In this paper we investigate the use of adversarial domain adaptation fo...
11/06/2018 ∙ by Johan Rohdin, et al. ∙ 0 ∙ share

read it
Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

In this work, we present an analysis of a DNN-based autoencoder for spee...
11/19/2018 ∙ by Ondrej Novotny, et al. ∙ 0 ∙ share

read it
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...
12/06/2018 ∙ by Oldřich Kodym, et al. ∙ 0 ∙ share

read it
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...
02/25/2019 ∙ by Martin Fajcik, et al. ∙ 0 ∙ share

read it
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...
02/22/2019 ∙ by Vojtech Mrazek, et al. ∙ 0 ∙ share

read it
Automated Circuit Approximation Method Driven by Data Distribution

We propose an application-tailored data-driven fully automated method fo...
03/11/2019 ∙ by Zdenek Vasicek, et al. ∙ 0 ∙ share

read it
Learning Feature Aggregation in Temporal Domain for Re-Identification

Person re-identification is a standard and established problem in the co...
03/12/2019 ∙ by Jakub Špaňhel, et al. ∙ 0 ∙ share

read it
Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

This work tackles the problem of learning a set of language specific aco...
04/08/2019 ∙ by Lucas Ondel, et al. ∙ 0 ∙ share

read it
Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition

In this work, we continue in our research on i-vector extractor for spea...
04/05/2019 ∙ by Ondrej Novotny, et al. ∙ 0 ∙ share

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

Sequence-to-sequence ASR models require large quantities of data to atta...
04/30/2019 ∙ by Murali Karthick Baskar, et al. ∙ 0 ∙ share

read it
Simulations in Rank-Based Büchi Automata Complementation

The long search for an optimal complementation construction for Büchi au...
05/17/2019 ∙ by Yu-Fang Chen, et al. ∙ 0 ∙ share

read it
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...
07/13/2019 ∙ by Nooshin Maghsoodi, et al. ∙ 0 ∙ share

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

The state-of-the-art approaches employ approximate computing to improve ...
06/11/2019 ∙ by Vojtech Mrazek, et al. ∙ 0 ∙ share

read it
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...
07/13/2019 ∙ by Hossein Zeinali, et al. ∙ 0 ∙ share

read it
Learning document embeddings along with their uncertainties

Majority of the text modelling techniques yield only point estimates of ...
08/20/2019 ∙ by Santosh Kesiraju, et al. ∙ 0 ∙ share

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

Autonomous driving is a dynamically growing field of research, where qua...
09/15/2019 ∙ by Adam Ligocki, et al. ∙ 0 ∙ share

read it
Segmentation of Defective Skulls from CT Data for Tissue Modelling

In this work we present a method of automatic segmentation of defective ...
11/20/2019 ∙ by Oldřich Kodym, et al. ∙ 0 ∙ share

read it
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...
12/02/2019 ∙ by Alberto Marchisio, et al. ∙ 0 ∙ share

read it
Audio Inpainting: Revisited and Reweighted

We deal with the problem of sparsity-based audio inpainting. A consequen...
01/08/2020 ∙ by Ondřej Mokrý, et al. ∙ 0 ∙ share

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

Energy efficiency of hardware accelerators of deep neural networks (DNN)...
02/21/2020 ∙ by Filip Vaverka, et al. ∙ 0 ∙ share

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

Approximate circuits have been developed to provide good tradeoffs betwe...
04/22/2020 ∙ by Vojtech Mrazek, et al. ∙ 0 ∙ share

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

There has been abundant research on the development of Approximate Circu...
04/22/2020 ∙ by Bharath Srinivas Prabakaran, et al. ∙ 0 ∙ share

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

Despite many successful applications, Cartesian Genetic Programming (CGP...
04/23/2020 ∙ by David Hodan, et al. ∙ 0 ∙ share

read it
Jointly Trained Transformers models for Spoken Language Translation

Conventional spoken language translation (SLT) systems are pipeline base...
04/25/2020 ∙ by Hari Krishna Vydana, et al. ∙ 0 ∙ share

read it
Multi-Agent Programming Contest 2019 FIT BUT Team solution

During our participation in MAPC 2019, we have developed two multi-agent...
06/17/2020 ∙ by Vaclav Uhlir, et al. ∙ 0 ∙ share

read it
Automatic Speech Recognition Benchmark for Air-Traffic Communications

Advances in Automatic Speech Recognition (ASR) over the last decade open...
06/18/2020 ∙ by Juan Zuluaga-Gomez, et al. ∙ 0 ∙ share

read it

Brno University of Technology

Featured Researchers