Papers › Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping

Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping

19 Sep 2023arXiv:2309.10667archive 2025-07-28

Subash Khanal, Srikumar Sastry, Aayush Dhakal, Nathan Jacobs

We focus on the task of soundscape mapping, which involves predicting the most probable sounds that could be perceived at a particular geographic location. We utilise recent state-of-the-art models to encode geotagged audio, a textual description of the audio, and an overhead image of its capture location using contrastive pre-training. The end result is a shared embedding space for the three modalities, which enables the construction of soundscape maps for any geographic region from textual or audio queries. Using the SoundingEarth dataset, we find that our approach significantly outperforms the existing SOTA, with an improvement of image-to-audio Recall@100 from 0.256 to 0.450. Our code is available at https://github.com/mvrl/geoclap.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2309.10667")

Code

Syntology Ran 5 of 10 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mvrl/geoclap officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 5 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
4ran
5unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mvrl/geoclap. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

build_transform mvrl/geoclap/geoclap/utilities/SATMAE_transform.py official repository ran no licence file found · pointer only · 38f07e336b29c0a5 · report
get_1d_sincos_pos_embed_from_grid mvrl/geoclap/geoclap/models/SATMAE.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 4bdd36eab04c3f62 · report
get_retrevial_metrics mvrl/geoclap/geoclap/metrics.py official repository ran no licence file found · pointer only · 3a569587facdd418 · report
read_csv mvrl/geoclap/geoclap/dataloader.py official repository ran no licence file found · pointer only · 7d232c101df226df · report
stratified_sample_df mvrl/geoclap/geoclap/miscs/compute_similarity.py official repository ran no licence file found · pointer only · abed70a10c6a4d1d · report
get_2d_sincos_pos_embed mvrl/geoclap/geoclap/models/SATMAE.py official repository unverified no licence file found · pointer only · 9417ae492629cf06 · report
get_2d_sincos_pos_embed_from_grid mvrl/geoclap/geoclap/models/SATMAE.py official repository unverified no licence file found · pointer only · 4fd80de79832745d · report
get_processed_audio mvrl/geoclap/geoclap/dataloader.py official repository unverified no licence file found · pointer only · 46a8aabfa19195d4 · report
get_processed_text mvrl/geoclap/geoclap/dataloader.py official repository unverified no licence file found · pointer only · cfde410a49fd6d24 · report
get_retrevial mvrl/geoclap/geoclap/metrics.py official repository unverified no licence file found · pointer only · d32a4eff3b49ec7b · report

Tasks

Cross-Modal Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval SoundingEarth GeoCLAP Image-to-sound R@100 0.434 #1 of 2 Archive leaderboard report
Cross-Modal Retrieval SoundingEarth GeoCLAP Median Rank 159 #1 of 2 Archive leaderboard report
Cross-Modal Retrieval SoundingEarth GeoCLAP Sound-to-image R@100 0.434 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections