@ARTICLE{Pondel-Sycz_Karolina_End-To-End_2024,
 author={Pondel-Sycz, Karolina and Pietrzak, Agnieszka Paula and Szymla, Julia},
 volume={vol. 70},
 number={No 2},
 journal={International Journal of Electronics and Telecommunications},
 pages={315-321},
 howpublished={online},
 year={2024},
 publisher={Polish Academy of Sciences Committee of Electronics and Telecommunications},
 abstract={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).},
 type={Article},
 title={End-To-End deep neural models for Automatic Speech Recognition for Polish Language},
 URL={http://ochroma.man.poznan.pl/Content/131788/7_4593_Sycz_sk1.pdf},
 doi={10.24425/ijet.2024.149547},
 keywords={Automatic Speech Recognition, Deep Neural Networks, End-To-End, Polish Language},
}