There is a newer version of the record available.

Published May 8, 2025 | Version v1
Software Restricted

Code : Differentiability of Voice Disorders Through Explainable AI

Authors/Creators

Description

 
Please see the new version.
 
Please cite the following article if using the above codes: 
Özcan, F. Differentiability of voice disorders through explainable AI. Sci Rep 15, 18250 (2025). https://doi.org/10.1038/s41598-025-03444-3
 
 
250ms_images.zip : The melspectrograms were generated from the pathological voices from the VOice ICar fEDerico II (VOICED) dataset, publicly available on https://archive.physionet.org/physiobank/database/voiced/ ..
 
transfer_learning.m :  
This file is used to transfer learning.
 
explainability.m : 
This code generates and saves the XAI map of a melspectrograme image correctly clssified with OcclusionSensitivity
 
average_deviation.m :
This file is used to generate the mean and standard deviation images of all the XAI maps for the defined class.

Files

Restricted

The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/15363306">Log in</a> to check if you have access.