# Parameterization of Sequence of MFCCs for DNN-based voice disorder detection

## TL;DR

This paper presents a DNN-based system for detecting common voice disorders from sustained vowel sounds, achieving high accuracy in a competitive challenge, with specific focus on parameterizing MFCC sequences.

## Contribution

The study introduces a novel parameterization approach for MFCC sequences tailored for DNN input in voice disorder detection, and reports competitive results in a standardized challenge.

## Key findings

- Achieved second-best score in the 2018 FEMH Voice Data Challenge
- Parameterization of MFCC sequences improved DNN performance
- Final model showed a 0.6% score improvement after adjustments

## Abstract

In this article a DNN-based system for detection of three common voice disorders (vocal nodules, polyps and cysts; laryngeal neoplasm; unilateral vocal paralysis) is presented. The input to the algorithm is (at least 3-second long) audio recording of sustained vowel sound /a:/. The algorithm was developed as part of the "2018 FEMH Voice Data Challenge" organized by Far Eastern Memorial Hospital and obtained score value (defined in the challenge specification) of 77.44. This was the second best result before final submission. Final challenge results are not yet known during writing of this document. The document also reports changes that were made for the final submission which improved the score value in cross-validation by 0.6% points.