In this paper, we present a spoken dialog system used for collecting data for future research in the field of dementia prediction from speech. The dialog system was used to collect the speech data of patients with mild cognitive deficits. The core task solved by the ...

Pre-trained models used in the transfer-learning scenario are recently becoming very popular. Such models benefit from the availability of large sets of unlabeled data. Two kinds of such models include the Wav2Vec 2.0 speech recognizer and T5 text-to-text transformer. In this paper, we&...

Appropriate prosodic phrasing of the input text is crucial for natural speech synthesis outputs. The presented paper focuses on using a Text-to-Text Transfer Transformer for predicting phrase boundaries in text and inspects the possibility of enriching the input text with more detailed ...

The task of grammatical error correction is a widely studied field of natural language processing where the traditional rule-based approaches compete with the machine learning methods. The rule-based approach benefits mainly from a wide knowledge base available for a given language. On ...

This paper presents a method for automatic sign language recognition that was utilized in the CVPR 2021 ChaLearn Challenge (RGB track). Our method is composed of several approaches combined in an ensemble scheme to perform isolated sign-gesture recognition. We combine modalities of vide...

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants and animals in the field is hindering the&#x...

A robust and accurate AI-driven system as an assistance tool for snake species identification has vast potential to help lower deaths and disabilities caused by snakebites. With that in mind, we prepared the SnakeCLEF 2021: Automatic Snake Species Identification Challenge with Country-Level&...

This paper describes the methods that were used for annotation, localization and pixel-wise parsing of the coral reefs from underwater images. The proposed system achieved competitive results in the third edition of ImageCLEFcoral 2021 challenge. Specifically, in case of annotation and local...

The main scope of this paper is to propose data fusion algorithms suitable for estimation of gantry crane hook tilt angles based on the MEMS accelerometer and gyroscope readings. Such methods should merge useful information from both these sensors into a better estimate than t...

The paper deals with development of active anti-sway feedback control method for gantry cranes. Inertial measurement unit is chosen as a load motion sensing device allowing to close a feedback loop. The paper provides guidelines for the successive steps of mathematical modelling, data-d...

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants and animals is hindering the aggregation of ...

The paper presents a method for image-based snake species identification. The proposed method is based on deep residual neural networks - ResNeSt, ResNeXt and ResNet - fine-tuned from ImageNet pre-trained checkpoints. We achieve performance improvements by: discarding predictions of species that&...

In this paper, we discuss some interesting features of training a special acoustic model for only one speaker with a constant acoustic background (acoustic channel). Currently, the LF-MMI method achieves the best results in many speech recognition tasks. A typical LF-MMI training proced...

Several challenges may arise when designing new user interfaces (UIs), e.g., because of communication between designers and developers, to which the detection of UI elements can help. The ImageCLEF DrawnUI 2021 challenge builds on the detection of such elements in two contest tasks:...

This work presents a novel method for image-to-image translation named X-Bridge. The method is based on a conditional adversarial network. X-Bridge is a supervised method build upon the Pix2pix approach, however, it extends the original system with an additional reconstruction path and ...

Automatic test case generation based on knowledge of a model is currently a challenge for many researchers and developers. This article describes the first of two complementary methods for test case generation for Function Block Diagram (FBD) models and grey-box testing. The first ...

In this paper, we continue to investigate the use of machine learning for the automatic detection of glottal closure instants (GCIs) from raw speech. We compare several deep one-dimensional convolutional neural network architectures on the same data and show that the InceptionV3 model&#...

Verification of the behaviour of new designs of rotor seals is a crucial phase necessary for their use in rotary machines. Therefore, experimental equipment for the verification of properties that have an effect on rotor dynamics is being developed in the test laboratories of ...

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a spoken term and estim...

The paper describes the process of automatic building of a personalized TTS system. The system was primarily developed for people facing the threat of voice loss; however, it can be used by anyone who wants to save his/her voice for any reason. Regarding the target g...