Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI Using Deep Learning: Benchmarking 2D and 3D Convolutional and Transformer Networks

8 January 2025

Abstract

Accurate segmentation of the vocal tract from magnetic resonance imaging (MRI) data is essential for various voice and speech applications. Manual segmentation is time intensive and susceptible to errors. This study aimed to evaluate the efficacy of deep learning algorithms for automatic vocal tract segmentation from 3D MRI.

View on arXiv

@article{erattakulangara2025_2501.06229,
  title={ Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI Using Deep Learning: Benchmarking 2D and 3D Convolutional and Transformer Networks },
  author={ Subin Erattakulangara and Karthika Kelat and Katie Burnham and Rachel Balbi and Sarah E. Gerard and David Meyer and Sajan Goud Lingala },
  journal={arXiv preprint arXiv:2501.06229},
  year={ 2025 }
}

Comments on this paper