VocSegMRI: Multimodal Learning for Precise Vocal Tract Segmentation in Real-time MRI

Accurately segmenting articulatory structures in real-time magnetic resonance imaging (rtMRI) remains challenging, as most existing methods rely almost entirely on visual cues. Yet synchronized acoustic and phonological signals provide complementary context that can enrich visual information and improve precision. In this paper, we introduce VocSegMRI, a multimodal framework that integrates video, audio, and phonological inputs through cross-attention fusion for dynamic feature alignment. To further enhance cross-modal representation, we incorporate a contrastive learning objective that improves segmentation performance even when the audio modality is unavailable at inference. Evaluated on a sub-set of USC-75 rtMRI dataset, our approach achieves state-of-the-art performance, with a Dice score of 0.95 and a 95th percentile Hausdorff Distance (HD_95) of 4.20 mm, outperforming both unimodal and multimodal baselines. Ablation studies confirm the contributions of cross-attention and contrastive learning to segmentation precision and robustness. These results highlight the value of integrative multimodal modeling for accurate vocal tract analysis.