End-To-End deep neural models for Automatic Speech Recognition for Polish Language

Authors

  • Karolina Pondel-Sycz Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland
  • Agnieszka Paula Pietrzak Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland
  • Julia Szymla Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland

DOI:

https://doi.org/10.24425/ijet.2024.149547

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).

Published

2024-06-25

How to Cite

Pondel-Sycz, Karolina, et al. “End-To-End Deep Neural Models for Automatic Speech Recognition for Polish Language”. International Journal of Electronics and Telecommunications, vol. 70, no. 2, June 2024, doi:10.24425/ijet.2024.149547.

Issue

Section

Artykuły

Most read articles by the same author(s)