SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation

2025/10/12 by Muna, Ummy Maria, Shawon, Md Mehedi Hasan, Jobayer, Md +3
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Sound (cs.SD)

paper · doi:10.48550/arxiv.2510.10719

Abstract

The automated analysis of phonocardiograms is vital for the early diagnosis of cardiovascular disease, yet supervised deep learning is often constrained by the scarcity of expert-annotated data. In this paper, we propose the Self-Supervised Dual-Path Prototypical Network (SS-DPPN), a foundation model for cardiac audio representation and classification from unlabeled data. The framework introduces a dual-path contrastive learning based architecture that simultaneously processes 1D waveforms and 2D spectrograms using a novel hybrid loss. For the downstream task, a metric-learning approach using a Prototypical Network was used that enhances sensitivity and produces well-calibrated and trustworthy predictions. SS-DPPN achieves state-of-the-art performance on four cardiac audio benchmarks. The framework demonstrates exceptional data efficiency with a fully supervised model on three-fold reduction in labeled data. Finally, the learned representations generalize successfully across lung sound classification and heart rate estimation. Our experiments and findings validate SS-DPPN as a robust, reliable, and scalable foundation model for physiological signals.

Citations

• Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning
• Heart Murmur and Abnormal PCG Detection via Wavelet Scattering Transform & a 1D-CNN
• Listen2YourHeart: A Self-Supervised Approach for Detecting Murmur in Heart-Beat Sounds
• MAE-AST: Masked Autoencoding Audio Spectrogram Transformer
• SSAST: Self-Supervised Audio Spectrogram Transformer
• Multi-Format Contrastive Learning of Audio Representations
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
• CLAR: Contrastive Learning of Auditory Representations
• A Simple Framework for Contrastive Learning of Visual Representations
• Self-Supervised Learning of Pretext-Invariant Representations
• Episode-based Prototype Generating Network for Zero-Shot Learning
• Representation Learning with Contrastive Predictive Coding
• Prototypical Networks for Few-shot Learning
• Temporal Convolutional Networks for Action Segmentation and Detection
• Deep Residual Learning for Image Recognition

Related

• Generative Deep Learning and Signal Processing for Data Augmentation of Cardiac Auscultation Signals: Improving Model Robustness Using Synthetic Audio
• Deep Learning Based Classification of Unsegmented Phonocardiogram Spectrograms Leveraging Transfer Learning
• CardioPHON: Quality assessment and self-supervised pretraining for screening of cardiac function based on phonocardiogram recordings
• Scaling to Multimodal and Multichannel Heart Sound Classification with Synthetic and Augmented Biosignals
• Classification of Heart Sounds Using Multi-Branch Deep Convolutional Network and LSTM-CNN