Suppression of Background Noise in Speech Signals with Artificial Neural Networks, Exemplarily Applied to Keyboard Sounds

Leonard Fricke, Jurij Kuzmic, Igor Vatolkin

2022

Abstract

The importance of remote voice communication has greatly increased during the COVID-19 pandemic. With that comes the problem of degraded speech quality because of background noise. While there can be many unwanted background sounds, this work focuses on dynamically suppressing keyboard sounds in speech signals by utilizing artificial neural networks. Based on the Mel spectrograms as inputs, the neural networks are trained to predict how much power of a frequency inside a time window has to be removed to suppress the keyboard sound. For that goal, we have generated audio signals combined from samples of two publicly available datasets with speaker and keyboard noise recordings. Additionally, we compare three network architectures with different parameter settings as well as an open-source tool RNNoise. The results from the experiments described in this paper show that artificial neural networks can be successfully applied to remove complex background noise from speech signals.

Paper Citation

in Harvard Style

Fricke L., Kuzmic J. and Vatolkin I. (2022). Suppression of Background Noise in Speech Signals with Artificial Neural Networks, Exemplarily Applied to Keyboard Sounds. In Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA; ISBN 978-989-758-611-8, SciTePress, pages 367-374. DOI: 10.5220/0011537400003332

in Bibtex Style

@conference{ncta22,
author={Leonard Fricke and Jurij Kuzmic and Igor Vatolkin},
title={Suppression of Background Noise in Speech Signals with Artificial Neural Networks, Exemplarily Applied to Keyboard Sounds},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA},
year={2022},
pages={367-374},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011537400003332},
isbn={978-989-758-611-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA
TI - Suppression of Background Noise in Speech Signals with Artificial Neural Networks, Exemplarily Applied to Keyboard Sounds
SN - 978-989-758-611-8
AU - Fricke L.
AU - Kuzmic J.
AU - Vatolkin I.
PY - 2022
SP - 367
EP - 374
DO - 10.5220/0011537400003332
PB - SciTePress