{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":104,"of_with_code":39,"tagged_in_all":104,"counts":{"archive_papers_tagged":104,"with_a_code_link":39,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":104,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/iterative-sound-source-localization-for","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":16,"n_constructed":0,"n_ran_checked":4,"n_instrument":12,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sound2vision-generating-diverse-visuals-from#ran","syntology_url":"https://syntology.ai/paper/2412.06209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06209"}},"official":{"repos":["postech-ami/Sound2Scene"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-critical-assessment-of-visual-sound-source","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-clip-help-sound-source-localization#ran","syntology_url":"https://syntology.ai/paper/2311.04066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04066"}},"official":{"repos":["swimmiing/ACL-SSL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/resilient-multiple-choice-learning-a-learned","slug":"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_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/resilient-multiple-choice-learning-a-learned#ran","syntology_url":"https://syntology.ai/paper/2311.01052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01052"}},"official":{"repos":["victorletzelter/code-rmcl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/audio-visual-instance-segmentation","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/audio-visual-grouping-network-for-sound#ran","syntology_url":"https://syntology.ai/paper/2303.17056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17056"}},"official":{"repos":["stonemo/avgn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/chaotic-world-a-large-and-challenging","slug":"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","slug":"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","slug":"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","slug":"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-closer-look-at-weakly-supervised-audio#ran","syntology_url":"https://syntology.ai/paper/2209.09634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09634"}},"official":{"repos":["stonemo/slavc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-predictive-learning-a","slug":"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","slug":"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","slug":"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},{"url":"/paper/joint-learning-of-visual-audio-saliency","slug":"joint-learning-of-visual-audio-saliency","title":"Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos","date":"2021-11-05","arxiv_id":"2111.08567","repositories_listed":1,"syntology":null},{"url":"/paper/odas-open-embedded-audition-system","slug":"odas-open-embedded-audition-system","title":"ODAS: Open embeddeD Audition System","date":"2021-03-05","arxiv_id":"2103.03954","repositories_listed":1,"syntology":null},{"url":"/paper/localize-to-binauralize-audio-spatialization","slug":"localize-to-binauralize-audio-spatialization","title":"Localize to Binauralize: Audio Spatialization From Visual Sound Source Localization","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/doanet-a-deep-dilated-convolutional-neural","slug":"doanet-a-deep-dilated-convolutional-neural","title":"DOANet: a deep dilated convolutional neural network approach for search and rescue with drone-embedded sound source localization","date":"2020-11-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-localize-sound-sources-in-visual","slug":"learning-to-localize-sound-sources-in-visual","title":"Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications","date":"2019-11-20","arxiv_id":"1911.09649","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-localize-sound-sources-in-visual#ran","syntology_url":"https://syntology.ai/paper/1911.09649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09649"}},"official":null}},{"url":"/paper/the-locata-challenge-acoustic-source","slug":"the-locata-challenge-acoustic-source","title":"The LOCATA Challenge: Acoustic Source Localization and Tracking","date":"2019-09-03","arxiv_id":"1909.01008","repositories_listed":1,"syntology":null},{"url":"/paper/direction-of-arrival-with-one-microphone-a","slug":"direction-of-arrival-with-one-microphone-a","title":"Direction of Arrival with One Microphone, a few LEGOs, and Non-Negative Matrix Factorization","date":"2018-08-28","arxiv_id":"1801.03740","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-scene-analysis-with-self","slug":"audio-visual-scene-analysis-with-self","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","date":"2018-04-10","arxiv_id":"1804.03641","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-networks-for-multiple-speaker","slug":"deep-neural-networks-for-multiple-speaker","title":"Deep Neural Networks for Multiple Speaker Detection and Localization","date":"2017-11-30","arxiv_id":"1711.11565","repositories_listed":1,"syntology":null},{"url":null,"slug":"a-wireless-self-calibrating-ultrasound","title":"A Wireless Self-Calibrating Ultrasound Microphone Array with Sub-Microsecond Synchronization","date":"2025-06-24","arxiv_id":"2506.19612","repositories_listed":0,"syntology":null},{"url":null,"slug":"shamans-sound-localization-with-hybrid-alpha","title":"SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer","date":"2025-06-23","arxiv_id":"2506.18954","repositories_listed":0,"syntology":null},{"url":null,"slug":"auralnet-hierarchical-attention-based-3d","title":"AuralNet: Hierarchical Attention-based 3D Binaural Localization of Overlapping Speakers","date":"2025-06-03","arxiv_id":"2506.02773","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-microphone-fault-tolerant-3d","title":"Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization","date":"2025-05-27","arxiv_id":"2505.20961","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusionrir-room-impulse-response","title":"DiffusionRIR: Room Impulse Response Interpolation using Diffusion Models","date":"2025-04-29","arxiv_id":"2504.20625","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sound-source-localization-with","title":"Improving Sound Source Localization with Joint Slot Attention on Image and Audio","date":"2025-04-21","arxiv_id":"2504.15118","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-trajectorir-database-room-acoustic","title":"The trajectoRIR Database: Room Acoustic Recordings Along a Trajectory of Moving Microphones","date":"2025-03-29","arxiv_id":"2503.23004","repositories_listed":0,"syntology":null},{"url":null,"slug":"eeg-based-decoding-of-sound-location","title":"EEG-Based Decoding of Sound Location: Comparing Free-Field to Headphone-Based Non-Individual HRTFs","date":"2025-03-13","arxiv_id":"2503.10783","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-robust-sound-source-localization","title":"CNN-based Robust Sound Source Localization with SRP-PHAT for the Extreme Edge","date":"2025-03-03","arxiv_id":"2503.02046","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-enhanced-dual-stream-feature-fusion","title":"Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained Model for Acoustic Traffic Monitoring","date":"2024-12-26","arxiv_id":"2412.19078","repositories_listed":0,"syntology":null},{"url":null,"slug":"soundloc3d-invisible-3d-sound-source","title":"SoundLoc3D: Invisible 3D Sound Source Localization and Classification Using a Multimodal RGB-D Acoustic Camera","date":"2024-12-22","arxiv_id":"2412.16861","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-weighted-spatial-likelihood-coding-for","title":"Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation","date":"2024-10-25","arxiv_id":"2410.19595","repositories_listed":0,"syntology":null},{"url":null,"slug":"tf-mamba-a-time-frequency-network-for-sound","title":"TF-Mamba: A Time-Frequency Network for Sound Source Localization","date":"2024-09-08","arxiv_id":"2409.05034","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-moving-sound-source-trajectories","title":"Leveraging Sound Source Trajectories for Universal Sound Separation","date":"2024-09-07","arxiv_id":"2409.04843","repositories_listed":0,"syntology":null},{"url":null,"slug":"configurable-doa-estimation-using-incremental","title":"Where's That Voice Coming? Continual Learning for Sound Source Localization","date":"2024-07-04","arxiv_id":"2407.03661","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-queried-target-sound-event-localization","title":"Text-Queried Target Sound Event Localization","date":"2024-06-23","arxiv_id":"2406.16058","repositories_listed":0,"syntology":null},{"url":null,"slug":"broadband-mems-microphone-arrays-with-reduced","title":"Broadband MEMS Microphone Arrays with Reduced Aperture Through 3D-Printed Waveguides","date":"2024-06-11","arxiv_id":"2406.07663","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-simulation-for-sound-source","title":"Audio Simulation for Sound Source Localization in Virtual Evironment","date":"2024-04-02","arxiv_id":"2404.01611","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-vsl-text-guided-visual-sound-source","title":"T-VSL: Text-Guided Visual Sound Source Localization in Mixtures","date":"2024-04-02","arxiv_id":"2404.01751","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-event-localization-and-classification","title":"Sound event localization and classification using WASN in Outdoor Environment","date":"2024-03-29","arxiv_id":"2403.20130","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-aggregation-in-joint-sound","title":"Feature Aggregation in Joint Sound Classification and Localization Neural Networks","date":"2023-10-29","arxiv_id":"2310.19063","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-source-localization-is-all-about-cross","title":"Sound Source Localization is All about Cross-Modal Alignment","date":"2023-09-19","arxiv_id":"2309.10724","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-3d-room-geometry-inference-with-a","title":"Data-driven 3D Room Geometry Inference with a Linear Loudspeaker Array and a Single Microphone","date":"2023-08-28","arxiv_id":"2308.14611","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-label-coding-for-end-to-end-sound-source","title":"Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays","date":"2023-04-15","arxiv_id":"2304.07512","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-to-visual-scene-generation-by-audio-to","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","date":"2023-03-30","arxiv_id":"2303.17490","repositories_listed":0,"syntology":null},{"url":null,"slug":"recnet-early-attention-guided-feature","title":"LOCUS: LOcalization with Channel Uncertainty and Sporadic Energy","date":"2023-02-18","arxiv_id":"2302.09409","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-acoustic-perception-for-automotive","title":"Real-Time Acoustic Perception for Automotive Applications","date":"2023-01-30","arxiv_id":"2301.12808","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-trajectory-localization-accuracy","title":"Improving trajectory localization accuracy via direction-of-arrival derivative estimation","date":"2022-12-07","arxiv_id":"2212.03470","repositories_listed":0,"syntology":null},{"url":null,"slug":"marginnce-robust-sound-localization-with-a","title":"MarginNCE: Robust Sound Localization with a Negative Margin","date":"2022-11-03","arxiv_id":"2211.01966","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-audio-visual-multi","title":"Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function","date":"2022-10-26","arxiv_id":"2210.14581","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-tracking-of-a-varying-number-of","title":"Position tracking of a varying number of sound sources with sliding permutation invariant training","date":"2022-10-26","arxiv_id":"2210.14536","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-two-dimensional-sound-source","title":"End-to-end Two-dimensional Sound Source Localization With Ad-hoc Microphone Arrays","date":"2022-10-16","arxiv_id":"2210.08484","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-proposal-based-paradigm-for-self-supervised","title":"A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emergency-vehicles-audio-detection-and","title":"Emergency Vehicles Audio Detection and Localization in Autonomous Driving","date":"2021-09-30","arxiv_id":"2109.14797","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-sound-source-localization-with","title":"A Survey of Sound Source Localization with Deep Learning Methods","date":"2021-09-08","arxiv_id":"2109.03465","repositories_listed":0,"syntology":null},{"url":null,"slug":"acousticfusion-fusing-sound-source","title":"AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments","date":"2021-08-03","arxiv_id":"2108.01246","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-normalization-multitasking-for-audio","title":"Dual Normalization Multitasking for Audio-Visual Sounding Object Localization","date":"2021-06-01","arxiv_id":"2106.00180","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-object-detection-from-audio","title":"Self-supervised object detection from audio-visual correspondence","date":"2021-04-13","arxiv_id":"2104.06401","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-self-supervised-learning-of","title":"Contrastive Self-Supervised Learning of Global-Local Audio-Visual Representations","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-framework-for-real-world","title":"Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization","date":"2020-12-10","arxiv_id":"2012.05533","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-of-discriminators-for-domain","title":"Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization","date":"2020-12-10","arxiv_id":"2012.05908","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multiple-sound-source-2d","title":"Learning Multiple Sound Source 2D Localization","date":"2020-12-10","arxiv_id":"2012.05515","repositories_listed":0,"syntology":null},{"url":null,"slug":"beamforming-for-measurements-under-disturbed","title":"Beamforming for measurements under disturbed propagation conditions using numerically calculated Green's functions","date":"2020-10-30","arxiv_id":"2010.16140","repositories_listed":0,"syntology":null},{"url":null,"slug":"blind-sound-source-localization-based-on-deep","title":"SSLIDE: Sound Source Localization for Indoors based on Deep Learning","date":"2020-10-27","arxiv_id":"2010.14420","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-listen-and-attend-co-attention-network","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","date":"2020-08-13","arxiv_id":"2008.05789","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-neural-audio-visual-sound","title":"Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling","date":"2020-07-28","arxiv_id":"2007.13976","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-we-need-sound-for-sound-source","title":"Do We Need Sound for Sound Source Localization?","date":"2020-07-11","arxiv_id":"2007.05722","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-tones-phase-coding-mtpc-of-interaural","title":"Multi-Tones' Phase Coding (MTPC) of Interaural Time Difference by Spiking Neural Network","date":"2020-07-07","arxiv_id":"2007.03274","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-can-attend-a-meeting-too-towards-a-human","title":"I can attend a meeting too! Towards a human-like telepresence avatar robot to attend meeting on your behalf","date":"2020-06-28","arxiv_id":"2006.15647","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-calibration-with-polynomial","title":"Audio-Visual Calibration with Polynomial Regression for 2-D Projection Using SVD-PHAT","date":"2020-02-12","arxiv_id":"2002.01440","repositories_listed":0,"syntology":null},{"url":null,"slug":"advances-in-online-audio-visual-meeting","title":"Advances in Online Audio-Visual Meeting Transcription","date":"2019-12-10","arxiv_id":"1912.04979","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","date":"2019-09-22","arxiv_id":"1909.09944","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-3-d-mapping-with-estimating","title":"Real-time 3-D Mapping with Estimating Acoustic Materials","date":"2019-09-16","arxiv_id":"1909.06998","repositories_listed":0,"syntology":null},{"url":null,"slug":"proceedings-of-the-locata-challenge-workshop","title":"Proceedings of the LOCATA Challenge Workshop -- a satellite event of IWAENC 2018","date":"2019-08-20","arxiv_id":"1811.08482","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-robust-3-d-sound-source-localization","title":"Fast and Robust 3-D Sound Source Localization with DSVD-PHAT","date":"2019-07-29","arxiv_id":"1907.12621","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirage-2d-source-localization-using","title":"Mirage: 2D Source Localization Using Microphone Pair Augmentation with Echoes","date":"2019-06-21","arxiv_id":"1906.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-signal-subspace-rotation-method-for","title":"A Signal Subspace Rotation Method for Localization of Multiple Wideband Sound Sources","date":"2019-06-20","arxiv_id":"1906.08847","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-robot-speech-recognition-using","title":"Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization","date":"2019-02-13","arxiv_id":"1902.05446","repositories_listed":0,"syntology":null},{"url":null,"slug":"svd-phat-a-fast-sound-source-localization","title":"SVD-PHAT: A Fast Sound Source Localization Method","date":"2019-02-11","arxiv_id":"1811.11785","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-localize-sound-source-in-visual","title":"Learning to Localize Sound Source in Visual Scenes","date":"2018-03-10","arxiv_id":"1803.03849","repositories_listed":0,"syntology":null},{"url":null,"slug":"phased-microphone-array-for-sound-source","title":"Phased Microphone Array for Sound Source Localization with Deep Learning","date":"2018-02-13","arxiv_id":"1802.04479","repositories_listed":0,"syntology":null}],"syntology_records":6,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/sound-source-localization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/sound-source-localization/papers/2","json":"/task/sound-source-localization/papers/2.json","rows":4},{"order":"ran","page":1,"of":1,"url":"/task/sound-source-localization/papers/ran/1","json":"/task/sound-source-localization/papers/ran/1.json","rows":6}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"51ea4d08b4d354b754dcc8180c0b53305eae4f1f413172d30ee05ce4791596a2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}