What type of study is this?

This is a Quantitative Study study.

September 17, 2025

A comparative study on state-of-the-art deep learning based vocal tract segmentation methods in volumetric sustained speech MRI

Key Points

Transfer learning significantly enhances performance with small datasets, improving segmentation outcomes.
Variability was observed in dice coefficient scores between different U-Net segmenters, impacting accuracy.
The analysis included four different U-Net architectures tested on a French speaker database to ensure consistency.
Findings highlight the strengths and weaknesses of state-of-the-art techniques, guiding future research in vocal tract MRI.

Abstract

Motivation: This work is motivated by the need to improve MRI-based quantitative assessments of vocal tract postures in speech and voice studies. Goal(s): The goal is to compare state-of-the-art segmentation methods in volumetric vocal tract MRI segmentation, and provide insights into the their effectiveness. Approach: This comparative study examines four different U-Net architectures. All networks are trained and tested on an open-source French speaker database in a consistent manner to assess their performance with limited data. Results: Our findings indicate that transfer learning is particularly effective when training with small datasets. Additionally, we identified variability in dice coefficient between different segmenters. Impact: This study informs researchers about various state-of-the-art segmentation methods for upper airway MRI. It emphasizes the strengths and weaknesses of each method and identifies which methods work efficiently under specific conditions.

AI에게 질문

Bookmark