| Issue |
Acta Acust.
Volume 8, 2024
|
|
|---|---|---|
| Article Number | 2 | |
| Number of page(s) | 8 | |
| Section | Audio Signal Processing and Transducers | |
| DOI | https://doi.org/10.1051/aacus/2023067 | |
| Published online | 09 January 2024 | |
Letter to the Editor
An experiment on an automated literature survey of data-driven speech enhancement methods
1
Communication Acoustics Lab, School of Electrical and Computer Engineering, Universidade Estadual de Campinas, Campinas – SP 13083-970, Brazil
2
NeuralMind, Campinas – SP, 13083-898, Brazil
3
ABB Corporate Research, SE-72226 Västerås, Sweden
4
The Marcus Wallenberg Laboratory for Sound and Vibration Research, Department of Engineering Mechanics, KTH Royal Institute of Technology, SE-10044 Stockholm, Sweden
* Corresponding author: a264372@dac.unicamp.br
Received:
1
November
2023
Accepted:
8
December
2023
The increasing number of scientific publications in acoustics, in general, presents difficulties in conducting traditional literature surveys. This work explores the use of a generative pre-trained transformer (GPT) model to automate a literature survey of 117 articles on data-driven speech enhancement methods. The main objective is to evaluate the capabilities and limitations of the model in providing accurate responses to specific queries about the papers selected from a reference human-based survey. While we see great potential to automate literature surveys in acoustics, improvements are needed to address technical questions more clearly and accurately.
Key words: Speech enhancement methods / Data-driven acoustics / Literature survey / Natural language processing / Large language models
© The Author(s), Published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.