An experiment on an automated literature survey of data-driven speech enhancement methods
This work addresses the difficulty of managing increasing publications for researchers in acoustics, but it is incremental as it applies an existing method to a new domain.
The authors tackled the challenge of conducting literature surveys in acoustics by using a GPT model to automate a survey of 116 articles on data-driven speech enhancement methods, evaluating its capabilities and limitations in providing accurate responses to specific queries, though improvements are needed for technical questions.
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.