# Reproducible Machine Learning-based Voice Pathology Detection: Introducing the Pitch Difference Feature

arXiv: https://arxiv.org/abs/2410.10537 · HTML: https://mlsanity.com/paper/2410.10537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 75 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Oversampling for Imbalanced Learning Based on K-Means and SMOTE](https://mlsanity.com/paper/1711.00837/) (2017)
- [TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch](https://mlsanity.com/paper/2310.17864/) (2023)
- [Voice Pathology Detection Using Deep Learning: a Preliminary Study](https://mlsanity.com/paper/1907.05905/) (2019)
- [Towards Robust Voice Pathology Detection](https://mlsanity.com/paper/1907.06129/) (2019)

## Built on by (most cited first, 1 of 1)

- [AI-Driven Acoustic Voice Biomarker-Based Hierarchical Classification of Benign Laryngeal Voice Disorders from Sustained Vowels](https://mlsanity.com/paper/2512.24628/) (2025)

## Abstract (arXiv)

Purpose: We introduce a novel methodology for voice pathology detection using the publicly available Saarbr"ucken Voice Database (SVD) and a robust feature set combining commonly used acoustic handcrafted features with two novel ones: pitch difference (relative variation in fundamental frequency) and NaN feature (failed fundamental frequency estimation). Methods: We evaluate six machine learning (ML) algorithms -- support vector machine, k-nearest neighbors, naive Bayes, decision tree, random forest, and AdaBoost -- using grid search for feasible hyperparameters and 20480 different feature subsets. Top 1000 classification models -- feature subset combinations for each ML algorithm are validated with repeated stratified cross-validation. To address class imbalance, we apply K-Means SMOTE to augment the training data. Results: Our approach achieves 85.61%, 84.69% and 85.22% unweighted average recall (UAR) for females, males and combined results respectively. We intentionally omit accuracy as it is a highly biased metric for imbalanced data. Conclusion: Our study demonstrates that by following the proposed methodology and feature engineering, there is a potential in detection of various voice pathologies using ML models applied to the simplest vocal task, a sustained utterance of the vowel /a:/. To enable easier use of our methodology and to support our claims, we provide a publicly available GitHub repository with DOI 10.5281/zenodo.13771573. Finally, we provide a REFORMS checklist to enhance readability, reproducibility and justification of our approach