An experiment on an automated literature survey of data-driven speech enhancement methods

TL;DR

This paper investigates using a GPT model to automate literature surveys in data-driven speech enhancement, assessing its effectiveness and limitations compared to traditional manual surveys.

Contribution

It demonstrates the potential of GPT models to automate literature reviews in acoustics and identifies areas for technical improvement.

Findings

GPT can generate relevant survey responses

Model shows limitations in technical accuracy

Automation can assist but not replace manual surveys

Abstract

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 116 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.