Research Article Open Access

Synthetic Data for AI-Driven Detection of Laryngeal Cancer

Abstract

This paper explores the use of Artificial Intelligence (AI) for detecting laryngeal cancer through synthetically generated voice data, an area with limited research. While previous studies have shown promise using real voice data, they often rely on proprietary datasets, with no publicly available models for replication. The authors address this gap by developing and open sourcing an AI model trained on synthetic voice data to distinguish between normal and diseased voices. The paper compares the performance of the model using synthetic and real voice data, discusses the methods used for data preparation and model training, and presents the resulting open-source model for public use. This work contributes to the growing body of research on AI and voice data, offering a valuable resource for further exploration in medical diagnostics.

Beenish Zia1*, Farshid Taghizadeh2

To read the full article Download Full Article | Visit Full Article