PSM: Learning Probabilistic Embeddings for Multi-scale Zero-Shot Soundscape Mapping
This work addresses the challenge of creating large-scale, dynamic soundscape maps for environmental monitoring and research, though it appears incremental as it builds on existing soundscape mapping approaches.
The authors tackled the problem of mapping soundscapes across Earth by developing a framework that learns probabilistic embeddings from multi-scale satellite imagery, audio, and text, outperforming state-of-the-art methods on their new GeoSound dataset and an existing dataset.
A soundscape is defined by the acoustic environment a person perceives at a location. In this work, we propose a framework for mapping soundscapes across the Earth. Since soundscapes involve sound distributions that span varying spatial scales, we represent locations with multi-scale satellite imagery and learn a joint representation among this imagery, audio, and text. To capture the inherent uncertainty in the soundscape of a location, we design the representation space to be probabilistic. We also fuse ubiquitous metadata (including geolocation, time, and data source) to enable learning of spatially and temporally dynamic representations of soundscapes. We demonstrate the utility of our framework by creating large-scale soundscape maps integrating both audio and text with temporal control. To facilitate future research on this task, we also introduce a large-scale dataset, GeoSound, containing over $300k$ geotagged audio samples paired with both low- and high-resolution satellite imagery. We demonstrate that our method outperforms the existing state-of-the-art on both GeoSound and the existing SoundingEarth dataset. Our dataset and code is available at https://github.com/mvrl/PSM.