WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction

--Mean Opinion Score (MOS) prediction for text-to-music systems requires evaluating both overall musical quality and text-prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence-level co-attention and optimal transport regularization. WhisQ employs the Whisper-Base pretrained model for temporal audio encoding and Qwen-3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for fine-grained cross-modal modeling. The architecture features specialized prediction pathways: OMQ is predicted from pooled audio embeddings, while T A leverages bidirectional sequence co-attention between audio and text. Sinkhorn optimal transport loss further enforce semantic alignment in the shared embedding space. On the MusicEval Track-1 dataset, WhisQ achieves substantial improvements over the baseline: 7% improvement in Spearman correlation for OMQ and 14% for T A. Ablation studies reveal that optimal transport regularization provides the largest performance gain (10% SRCC improvement), demonstrating the importance of explicit cross-modal alignment for text-to-music evaluation.