Optimizing Domain-Adaptive Self-Supervised Learning for Clinical Voice-Based Disease Classification

TL;DR

This paper improves domain-adaptive self-supervised learning for clinical voice analysis by optimizing loss functions, normalization, and masking strategies, leading to better disease classification performance on a multi-institutional dataset.

Contribution

It systematically investigates and identifies optimal configurations of SSL components for health-related audio, achieving superior results over standard methods.

Findings

Optimized SSL configuration improves Macro F1 score from 0.663 to 0.688.

Content-aware masking enhances performance by emphasizing informative regions.

MA-Error loss increases robustness in clinical voice classification.

Abstract

The human voice is a promising non-invasive digital biomarker, yet deep learning for voice-based health analysis is hindered by data scarcity and domain mismatch, where models pre-trained on general audio fail to capture the subtle pathological features characteristic of clinical voice data. To address these challenges, we investigate domain-adaptive self-supervised learning (SSL) with Masked Autoencoders (MAE) and demonstrate that standard configurations are suboptimal for health-related audio. Using the Bridge2AI-Voice dataset, a multi-institutional collection of pathological voices, we systematically examine three performance-critical factors: reconstruction loss (Mean Absolute Error vs. Mean Squared Error), normalization (patch-wise vs. global), and masking (random vs. content-aware). Our optimized design, which combines Mean Absolute Error (MA-Error) loss, patch-wise normalization, and content-aware masking, achieves a Macro F1 of $0.688 \pm 0.009$ (over 10 fine-tuning runs), outperforming a strong out-of-domain SSL baseline pre-trained on large-scale general audio, which has a Macro F1 of $0.663 \pm 0.011$. The results show that MA-Error loss improves robustness and content-aware masking boosts performance by emphasizing information-rich regions. These findings highlight the importance of component-level optimization in data-constrained medical applications that rely on audio data.