SMSAT: A Multimodal Acoustic Dataset and Deep Contrastive Learning Framework for Affective and Physiological Modeling of Spiritual Meditation
arXiv Preprint Archive May 1, 2025 Ahmad Suleman, Yazeed Alkhrijah, Misha Urooj Khan et al.
A new dataset (SMSAT) of acoustic time series signals was collected while participants listened to spiritual meditation, music, or natural silence. A contrastive-learning audio encoder achieved 99.99% classification accuracy in distinguishing the three conditions, and a deep-learning model (CAM) using 25 handcrafted and learned features also reached 99.99% accuracy for affective state classification. Pairwise t-tests showed significant differences in cardiac response characteristics, with spiritual meditation inducing more pronounced physiological fluctuations than the other conditions. The authors argue the dataset and framework can support stress monitoring, mental well-being, and therapeutic audio interventions.