{"url":"/task/sound-source-localization","name":"Sound Source Localization","slug":"sound-source-localization","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":104,"papers_with_code":39,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/sound-source-localization-on","slug":"sound-source-localization-on","dataset":"^(#$!@#$)(()))******","dataset_url":null,"rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"YOLO","paper_title":"ODAS: Open embeddeD Audition System","paper_url":"/paper/odas-open-embedded-audition-system","paper_date":"2021-03-05","arxiv_id":"2103.03954","code_links":[{"title":"introlab/odas","url":"https://github.com/introlab/odas"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":39,"tagged_in_all":104,"items":[{"url":"/paper/iterative-sound-source-localization-for","title":"Iterative Sound Source Localization for Unknown Number of Sources","date":"2022-06-24","arxiv_id":"2206.12273","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-tracking-based-training-of","title":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","date":"2021-10-29","arxiv_id":"2111.00030","repositories_listed":2,"syntology":null},{"url":"/paper/hearing-and-seeing-through-clip-a-framework","title":"Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization","date":"2025-05-08","arxiv_id":"2505.05343","repositories_listed":1,"syntology":null},{"url":"/paper/object-aware-sound-source-localization-via","title":"Object-aware Sound Source Localization via Audio-Visual Scene Understanding","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sound2vision-generating-diverse-visuals-from","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","date":"2024-12-09","arxiv_id":"2412.06209","repositories_listed":1,"syntology":{"n":18,"n_ran":5,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/a-critical-assessment-of-visual-sound-source","title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio","date":"2024-10-01","arxiv_id":"2410.01020","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-sound-source-localization-via-false","title":"Enhancing Sound Source Localization via False Negative Elimination","date":"2024-08-29","arxiv_id":"2408.16448","repositories_listed":1,"syntology":null},{"url":"/paper/wav2pos-sound-source-localization-using","title":"wav2pos: Sound Source Localization using Masked Autoencoders","date":"2024-08-28","arxiv_id":"2408.15771","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-sight-and-sound-advanced-sound","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","date":"2024-07-18","arxiv_id":"2407.13676","repositories_listed":1,"syntology":null},{"url":"/paper/ipdnet-a-universal-direct-path-ipd-estimation","title":"IPDnet: A Universal Direct-Path IPD Estimation Network for Sound Source Localization","date":"2024-05-11","arxiv_id":"2405.07021","repositories_listed":1,"syntology":null},{"url":"/paper/semipl-a-semi-supervised-method-for-event","title":"SemiPL: A Semi-supervised Method for Event Sound Source Localization","date":"2024-04-30","arxiv_id":"2404.19615","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-visually-localize-sound-sources","title":"Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge","date":"2024-03-26","arxiv_id":"2403.17420","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-distance-estimation-in-enclosures","title":"Speaker Distance Estimation in Enclosures from Single-Channel Audio","date":"2024-03-26","arxiv_id":"2403.17514","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-output-architecture-for-sound","title":"Eliminating Quantization Errors in Classification-Based Sound Source Localization","date":"2023-11-21","arxiv_id":"2311.12305","repositories_listed":1,"syntology":null},{"url":"/paper/can-clip-help-sound-source-localization","title":"Can CLIP Help Sound Source Localization?","date":"2023-11-07","arxiv_id":"2311.04066","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":10}},{"url":"/paper/resilient-multiple-choice-learning-a-learned","title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis","date":"2023-11-02","arxiv_id":"2311.01052","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/audio-visual-instance-segmentation","title":"Audio-Visual Instance Segmentation","date":"2023-10-28","arxiv_id":"2310.18709","repositories_listed":1,"syntology":null},{"url":"/paper/novel-view-acoustic-synthesis-from-3d","title":"Novel-View Acoustic Synthesis from 3D Reconstructed Rooms","date":"2023-10-23","arxiv_id":"2310.15130","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-spatial-integration-and","title":"Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization","date":"2023-08-11","arxiv_id":"2308.06087","repositories_listed":1,"syntology":null},{"url":"/paper/induction-network-audio-visual-modality-gap","title":"Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization","date":"2023-08-09","arxiv_id":"2308.04767","repositories_listed":1,"syntology":null},{"url":"/paper/dual-input-neural-networks-for-positional","title":"Dual input neural networks for positional sound source localization","date":"2023-08-08","arxiv_id":"2308.04169","repositories_listed":1,"syntology":null},{"url":"/paper/fn-ssl-full-band-and-narrow-band-fusion-for","title":"FN-SSL: Full-Band and Narrow-Band Fusion for Sound Source Localization","date":"2023-05-31","arxiv_id":"2305.19610","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-grouping-network-for-sound","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","date":"2023-03-29","arxiv_id":"2303.17056","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/chaotic-world-a-large-and-challenging","title":"Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/flowgrad-using-motion-for-visual-sound-source","title":"FlowGrad: Using Motion for Visual Sound Source Localization","date":"2022-11-15","arxiv_id":"2211.08367","repositories_listed":1,"syntology":null},{"url":"/paper/hear-the-flow-optical-flow-based-self","title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization","date":"2022-11-06","arxiv_id":"2211.03019","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-weakly-supervised-audio","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","date":"2022-08-30","arxiv_id":"2209.09634","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/self-supervised-predictive-learning-a","title":"Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes","date":"2022-03-25","arxiv_id":"2203.13412","repositories_listed":1,"syntology":null},{"url":"/paper/hrtf-measurement-for-accurate-identification","title":"HRTF measurement for accurate sound localization cues","date":"2022-03-07","arxiv_id":"2203.03166","repositories_listed":1,"syntology":null},{"url":"/paper/visual-sound-localization-in-the-wild-by","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","date":"2022-02-13","arxiv_id":"2202.06406","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}