Cross-Modal Urban Sensing: Evaluating Sound-Vision Alignment Across Street-Level and Aerial Imagery
This work addresses the problem of integrating sound into geospatial analysis for urban sensing, offering incremental insights by comparing existing methods on new data.
The study investigated the alignment between urban sounds and visual scenes by comparing visual representation strategies using geo-referenced data from London, New York, and Tokyo, finding that street view embeddings showed stronger alignment with sounds than segmentation outputs, while remote sensing segmentation was more effective for ecological categories.
Environmental soundscapes convey substantial ecological and social information regarding urban environments; however, their potential remains largely untapped in large-scale geographic analysis. In this study, we investigate the extent to which urban sounds correspond with visual scenes by comparing various visual representation strategies in capturing acoustic semantics. We employ a multimodal approach that integrates geo-referenced sound recordings with both street-level and remote sensing imagery across three major global cities: London, New York, and Tokyo. Utilizing the AST model for audio, along with CLIP and RemoteCLIP for imagery, as well as CLIPSeg and Seg-Earth OV for semantic segmentation, we extract embeddings and class-level features to evaluate cross-modal similarity. The results indicate that street view embeddings demonstrate stronger alignment with environmental sounds compared to segmentation outputs, whereas remote sensing segmentation is more effective in interpreting ecological categories through a Biophony--Geophony--Anthrophony (BGA) framework. These findings imply that embedding-based models offer superior semantic alignment, while segmentation-based methods provide interpretable links between visual structure and acoustic ecology. This work advances the burgeoning field of multimodal urban sensing by offering novel perspectives for incorporating sound into geospatial analysis.