PSM: Learning Probabilistic Embeddings for Multi-scale Zero-Shot Soundscape Mapping

TL;DR

This paper introduces PSM, a probabilistic multi-scale soundscape mapping framework that integrates satellite imagery, audio, and text to create dynamic, large-scale soundscape maps with a new dataset, GeoSound.

Contribution

The work presents a novel probabilistic embedding approach for multi-scale soundscape mapping and introduces the GeoSound dataset for large-scale, geotagged audio and imagery data.

Findings

Our method outperforms state-of-the-art on GeoSound and SoundingEarth datasets.

The probabilistic representation captures uncertainty in soundscape mapping.

Fusion of satellite imagery, audio, and metadata improves spatial-temporal mapping accuracy.

Abstract

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.