Fully Quantum Vowel Recognition

Authors

DOI:

https://doi.org/10.24425/ijet.2026.6339

Abstract

This paper presents the results of using a quantum machine learning algorithm for the task of vowel recognition. It compares computation times and accuracy results of different circuit depths in a simulated quantum environment. The paper proposes a fully quantum neural network using 4 qubits as feature maps with formant frequencies as input features. It compares the results of binary classification and the more problematic multiclass classification in quantum machine learning. The results show very high accuracy of around 97% for binary, 80% for 3 classes, 70% for 4 classes, and 50% for all 5 classes. The quantum neural networks were first pre-trained using a simulator and then evaluated on the real quantum computer Odra 5 to assess the impact of noise and hardware configuration on the performance of the trained quantum circuits.

Downloads

Published

2026-10-29

How to Cite

Kucharski, Mateusz, and Radosław Idzikowski. “Fully Quantum Vowel Recognition ”. International Journal of Electronics and Telecommunications, vol. 72, no. 4, Oct. 2026, pp. 1-7, doi:10.24425/ijet.2026.6339.

Issue

Section

Artykuły