Is Noise Reduction Improving Open-Source ASR Transcription Engines Quality?

Asma Trabelsi, Laurent Werey, Sébastien Warichet, Emmanuel Helbert

2024

Abstract

Transcription has becoming an important task on the field of Artificial Intelligence and Machine Learning. Much research has focused on such a field so that we find a lot of paid and open-source ASR solutions. The choose of the best solution is crucial. Open source ones seems to be appropriate especially for companies that would maintain the aspect of data sovereignty. Vosk and Whisper are ASR open-source tools that have been revolutionized this last period. The first idea of this paper is to compare these two solutions in term of Word Error Rate (WER) to conclude who performs best. In the meantime, a lot of models aroused focusing on removing disturbing noises (such as dog barks, child screams, etc) during remote communication. The second idea of the paper is to study the influence of such models applied prior to the transcription service on the quality of the communication transcription. In our study, we focused on voice mail transcription use case.

Paper Citation

in Harvard Style

Trabelsi A., Werey L., Warichet S. and Helbert E. (2024). Is Noise Reduction Improving Open-Source ASR Transcription Engines Quality?. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1221-1228. DOI: 10.5220/0012457100003636

in Bibtex Style

@conference{icaart24,
author={Asma Trabelsi and Laurent Werey and Sébastien Warichet and Emmanuel Helbert},
title={Is Noise Reduction Improving Open-Source ASR Transcription Engines Quality?},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1221-1228},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012457100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Is Noise Reduction Improving Open-Source ASR Transcription Engines Quality?
SN - 978-989-758-680-4
AU - Trabelsi A.
AU - Werey L.
AU - Warichet S.
AU - Helbert E.
PY - 2024
SP - 1221
EP - 1228
DO - 10.5220/0012457100003636
PB - SciTePress