Voice disorders significantly impact patient quality of life, yet non-invasive automated diagnosis remains under-explored due to both the scarcity of pathological voice data, and the variability in recording sources. This work introduces MVP (Multi-source Voice Pathology detection), a novel approach that leverages transformers operating directly on raw voice signals. We explore three fusion strategies to combine sentence reading and sustained vowel recordings: waveform concatenation, intermediate feature fusion, and decision-level combination. Empirical validation across the German, Portuguese, and Italian languages shows that intermediate feature fusion using transformers best captures the complementary characteristics of both recording types. Our approach achieves up to +13% AUC improvement over single-source methods.
This research introduces a novel AI techniques as Mixture-of-Experts Transformers with Group Relative Policy Optimization (GRPO) for voice health care applications on voice pathology detection. With the architectural innovations, we adopt advanced training paradigms inspired by reinforcement learning, namely Proximal Policy Optimization (PPO) and Group-wise Regularized Policy Optimization (GRPO), to enhance model stability and performance. Experiments conducted on a synthetically generated voice pathology dataset demonstrate that our proposed models significantly improve diagnostic accuracy, F1 score, and ROC-AUC compared to conventional approaches. These findings underscore the potential of integrating transformer architectures with novel training strategies to advance automated voice pathology detection and ultimately contribute to more effective healthcare delivery. The code we used to train and evaluate our models is available at https://github.com/enkhtogtokh/voicegrpo
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