This article concerns research on deep learning models (DNN) used for automatic speech recognition (ASR). In such systems, recognition is based on Mel Frequency Cepstral Coefficients (MFCC) acoustic features and spectrograms. The latest ASR technologies are based on convolutional neural networks (CNNs), recurrent neural networks (RNNs) and Transformers. The article presents an analysis of modern artificial intelligence algorithms adapted for automatic recognition of the Polish language. The differences between conventional architectures and ASR DNN End-To-End (E2E) models are discussed. Preliminary tests of five selected models (QuartzNet, FastConformer, Wav2Vec 2.0 XLSR, Whisper and ESPnet Model Zoo) on Mozilla Common Voice, Multilingual LibriSpeech and VoxPopuli databases are demonstrated. Tests were conducted for clean audio signal, signal with bandwidth limitation and degraded. The tested models were evaluated on the basis of Word Error Rate (WER).

The paper presents analysis of the possibility of using selected hash functions submitted for the SHA-3 competition in the SDEx encryption method. The group of these functions will include the finalists of the SHA-3 competition, i.e. BLAKE, Grøstl, JH, Keccak, Skein. The aim of the analysis is to develop more secure and faster cryptographic algorithm compared to the current version of the SDEx method with SHA- 512 and the AES algorithm. When considering the speed of algorithms, mainly the software implementation will be taken into account, as it is the most commonly used.