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

Author(s)

dos Santos, Arthur ; Pereira, Jayr ; Nogueira, Rodrigo ; Masiero, Bruno ; Tavallaey, Shiva Sander ; Zea, Elias

• Document type: Journal article
• Source: ACTA ACUSTICA; v. 8, p. 8-pg., 2024-01-09.

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 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. (AU)

• FAPESP's process: 22/16168-7 - Separation of audio objects based on the principle of sparsity
• Grantee: Arthur Nicholas dos Santos
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• FAPESP's process: 17/08120-6 - 3D-Audio. Sampling, encoding and reproduction of spatial audio
• Grantee: Bruno Sanches Masiero
• Support Opportunities: Research Grants - Young Investigators Grants
• FAPESP's process: 19/22795-1 - Sound object separation based on the principle of sparsity
• Grantee: Arthur Nicholas dos Santos
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)