{"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-event-localization-and-detection","name":"Sound Event Localization and Detection","slug":"sound-event-localization-and-detection","description_markdown":"Given multichannel audio input, a sound event detection and localization (SELD) system outputs a temporal activation track for each of the target sound classes, along with one or more corresponding spatial trajectories when the track indicates activity. This results in a spatio-temporal characterization of the acoustic scene that can be used in a wide range of machine cognition tasks, such as inference on the type of environment, self-localization, navigation without visual input or with occluded targets, tracking of specific types of sound sources, smart-home applications, scene visualization systems, and audio surveillance, among others.","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":65,"papers_with_code":35,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":9,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/sound-event-localization-and-detection-on-1","slug":"sound-event-localization-and-detection-on-1","dataset":"STARSS22","dataset_url":"/dataset/starss22","rows_in_archive":2,"metrics":["Class-dependent localization error","Class-dependent localization recall","location-dependent F1-score (macro)","location-dependent F1-score (micro)","Localization-dependent error rate (20°)"],"first_row_in_archive_order":{"model":"Baseline (FOA)","paper_title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","paper_url":"/paper/starss22-a-dataset-of-spatial-recordings-of","paper_date":"2022-06-04","arxiv_id":"2206.01948","code_links":[{"title":"sharathadavanne/seld-dcase2022","url":"https://github.com/sharathadavanne/seld-dcase2022"},{"title":"prerak23/dir_srcmic_doa","url":"https://github.com/prerak23/dir_srcmic_doa"}],"syntology":null}},{"leaderboard":"/sota/sound-event-localization-and-detection-on-2","slug":"sound-event-localization-and-detection-on-2","dataset":"PodcastFillers","dataset_url":"/dataset/podcastfillers","rows_in_archive":2,"metrics":["event-based F1 score"],"first_row_in_archive_order":{"model":"AVC-FillerNet","paper_title":"Filler Word Detection and Classification: A Dataset and Benchmark","paper_url":"/paper/filler-word-detection-and-classification-a","paper_date":"2022-03-28","arxiv_id":"2203.15135","code_links":[{"title":"gzhu06/PodcastFillers_Utils","url":"https://github.com/gzhu06/PodcastFillers_Utils"}],"syntology":null}},{"leaderboard":"/sota/sound-event-localization-and-detection-on","slug":"sound-event-localization-and-detection-on","dataset":"L3DAS21","dataset_url":"/dataset/l3das21","rows_in_archive":1,"metrics":["SELD score"],"first_row_in_archive_order":{"model":"DualQSELD-TCN (parallel)","paper_title":"Dual Quaternion Ambisonics Array for Six-Degree-of-Freedom Acoustic Representation","paper_url":"/paper/dual-quaternion-ambisonics-array-for-six","paper_date":"2022-04-04","arxiv_id":"2204.01851","code_links":[{"title":"ispamm/dualqseld-tcn","url":"https://github.com/ispamm/dualqseld-tcn"}],"syntology":null}},{"leaderboard":"/sota/sound-event-localization-and-detection-on-3","slug":"sound-event-localization-and-detection-on-3","dataset":"RWCP Sound Scene Database","dataset_url":"/dataset/rwcp-sound-scene-database","rows_in_archive":1,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"STL-SNN","paper_title":"A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks","paper_url":"/paper/a-synapse-threshold-synergistic-learning","paper_date":"2022-06-10","arxiv_id":"2206.06129","code_links":[{"title":"sunhongze/STL-SNN","url":"https://github.com/sunhongze/STL-SNN"}],"syntology":null}},{"leaderboard":"/sota/sound-event-localization-and-detection-on-tau-1","slug":"sound-event-localization-and-detection-on-tau-1","dataset":"TAU-NIGENS Spatial Sound Events 2021","dataset_url":"/dataset/tau-nigens-spatial-sound-events-2021","rows_in_archive":1,"metrics":["ER≤20°","F1≤20°","LE-CD","LR-CD"],"first_row_in_archive_order":{"model":"SALSA-FOA","paper_title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","paper_url":"/paper/salsa-spatial-cue-augmented-log-spectrogram","paper_date":"2021-10-01","arxiv_id":"2110.00275","code_links":[{"title":"thomeou/SALSA","url":"https://github.com/thomeou/SALSA"}],"syntology":null}}],"datasets":[{"url":"/dataset/starss23","name":"STARSS23","full_name":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","num_papers_in_archive":21},{"url":"/dataset/starss22","name":"STARSS22","full_name":"Sony-TAu Realistic Spatial Soundscapes 2022","num_papers_in_archive":19},{"url":"/dataset/l3das22","name":"L3DAS22","full_name":"","num_papers_in_archive":13},{"url":"/dataset/l3das21","name":"L3DAS21","full_name":"","num_papers_in_archive":6},{"url":"/dataset/podcastfillers","name":"PodcastFillers","full_name":"","num_papers_in_archive":5},{"url":"/dataset/tau-nigens-spatial-sound-events-2021","name":"TAU-NIGENS Spatial Sound Events 2021","full_name":"TAU-NIGENS Spatial Sound Events 2021","num_papers_in_archive":4},{"url":"/dataset/tau-nigens-spatial-sound-events-2020","name":"TAU-NIGENS Spatial Sound Events 2020","full_name":"TAU-NIGENS Spatial Sound Events 2020","num_papers_in_archive":2},{"url":"/dataset/bgg-dataset","name":"BGG dataset","full_name":"PUBG Gun Sound Dataset","num_papers_in_archive":1},{"url":"/dataset/rwcp-sound-scene-database","name":"RWCP Sound Scene Database","full_name":"RWCP Sound Scene Database","num_papers_in_archive":1}],"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":1,"rows_per_page":100,"shown":65,"of":65,"of_with_code":35,"tagged_in_all":65,"counts":{"archive_papers_tagged":65,"with_a_code_link":35,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":65,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/salsa-lite-a-fast-and-effective-feature-for","slug":"salsa-lite-a-fast-and-effective-feature-for","title":"SALSA-Lite: A Fast and Effective Feature for Polyphonic Sound Event Localization and Detection with Microphone Arrays","date":"2021-11-16","arxiv_id":"2111.08192","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/salsa-lite-a-fast-and-effective-feature-for#ran","syntology_url":"https://syntology.ai/paper/2111.08192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08192"}},"official":{"repos":["thomeou/salsa-lite"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/overview-and-evaluation-of-sound-event","slug":"overview-and-evaluation-of-sound-event","title":"Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019","date":"2020-09-06","arxiv_id":"2009.02792","repositories_listed":4,"syntology":null},{"url":"/paper/pseldnets-pre-trained-neural-networks-on","slug":"pseldnets-pre-trained-neural-networks-on","title":"PSELDNets: Pre-trained Neural Networks on Large-scale Synthetic Datasets for Sound Event Localization and Detection","date":"2024-11-10","arxiv_id":"2411.06399","repositories_listed":2,"syntology":null},{"url":"/paper/sound-event-localization-and-detection-for","slug":"sound-event-localization-and-detection-for","title":"Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains","date":"2022-09-05","arxiv_id":"2209.01802","repositories_listed":2,"syntology":null},{"url":"/paper/starss22-a-dataset-of-spatial-recordings-of","slug":"starss22-a-dataset-of-spatial-recordings-of","title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","date":"2022-06-04","arxiv_id":"2206.01948","repositories_listed":2,"syntology":null},{"url":"/paper/multi-accdoa-localizing-and-detecting","slug":"multi-accdoa-localizing-and-detecting","title":"Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training","date":"2021-10-14","arxiv_id":"2110.07124","repositories_listed":2,"syntology":null},{"url":"/paper/accdoa-activity-coupled-cartesian-direction","slug":"accdoa-activity-coupled-cartesian-direction","title":"ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection","date":"2020-10-29","arxiv_id":"2010.15306","repositories_listed":2,"syntology":null},{"url":"/paper/a-dataset-of-reverberant-spatial-sound-scenes","slug":"a-dataset-of-reverberant-spatial-sound-scenes","title":"A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection","date":"2020-06-02","arxiv_id":"2006.01919","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-dataset-of-reverberant-spatial-sound-scenes#ran","syntology_url":"https://syntology.ai/paper/2006.01919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.01919"}},"official":null}},{"url":"/paper/seld-tcn-sound-event-localization-detection","slug":"seld-tcn-sound-event-localization-detection","title":"SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks","date":"2020-03-03","arxiv_id":"2003.01609","repositories_listed":2,"syntology":null},{"url":"/paper/reverberation-based-features-for-sound-event","slug":"reverberation-based-features-for-sound-event","title":"Reverberation-based Features for Sound Event Localization and Detection with Distance Estimation","date":"2025-04-11","arxiv_id":"2504.08644","repositories_listed":1,"syntology":null},{"url":"/paper/mvanet-multi-stage-video-attention-network","slug":"mvanet-multi-stage-video-attention-network","title":"MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation","date":"2024-11-21","arxiv_id":"2411.14153","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-sound-event-localization-and","slug":"real-time-sound-event-localization-and","title":"Real-Time Sound Event Localization and Detection: Deployment Challenges on Edge Devices","date":"2024-09-18","arxiv_id":"2409.11700","repositories_listed":1,"syntology":null},{"url":"/paper/learning-multi-target-tdoa-features-for-sound","slug":"learning-multi-target-tdoa-features-for-sound","title":"Learning Multi-Target TDOA Features for Sound Event Localization and Detection","date":"2024-08-30","arxiv_id":"2408.17166","repositories_listed":1,"syntology":null},{"url":"/paper/mff-einv2-multi-scale-feature-fusion-across","slug":"mff-einv2-multi-scale-feature-fusion-across","title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","date":"2024-06-13","arxiv_id":"2406.08771","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mff-einv2-multi-scale-feature-fusion-across#ran","syntology_url":"https://syntology.ai/paper/2406.08771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08771"}},"official":{"repos":["muuda/MFF-EINV2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhanced-sound-event-localization-and","slug":"enhanced-sound-event-localization-and","title":"Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes","date":"2024-01-29","arxiv_id":"2401.17129","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-scaper-a-library-to-simulate-and","slug":"spatial-scaper-a-library-to-simulate-and","title":"Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms","date":"2024-01-19","arxiv_id":"2401.12238","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":6,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spatial-scaper-a-library-to-simulate-and#ran","syntology_url":"https://syntology.ai/paper/2401.12238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12238"}},"official":{"repos":["iranroman/spatialscaper"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-memory-meta-learning-with","slug":"selective-memory-meta-learning-with","title":"Selective-Memory Meta-Learning with Environment Representations for Sound Event Localization and Detection","date":"2023-12-27","arxiv_id":"2312.16422","repositories_listed":1,"syntology":null},{"url":"/paper/fusion-of-audio-and-visual-embeddings-for","slug":"fusion-of-audio-and-visual-embeddings-for","title":"Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection","date":"2023-12-14","arxiv_id":"2312.09034","repositories_listed":1,"syntology":null},{"url":"/paper/w2v-seld-a-sound-event-localization-and","slug":"w2v-seld-a-sound-event-localization-and","title":"w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training","date":"2023-12-12","arxiv_id":"2312.06907","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-geometrical-acoustic-simulations","slug":"leveraging-geometrical-acoustic-simulations","title":"Leveraging Geometrical Acoustic Simulations of Spatial Room Impulse Responses for Improved Sound Event Detection and Localization","date":"2023-09-06","arxiv_id":"2309.03337","repositories_listed":1,"syntology":null},{"url":"/paper/starss23-an-audio-visual-dataset-of-spatial","slug":"starss23-an-audio-visual-dataset-of-spatial","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","date":"2023-06-15","arxiv_id":"2306.09126","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/starss23-an-audio-visual-dataset-of-spatial#ran","syntology_url":"https://syntology.ai/paper/2306.09126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09126"}},"official":{"repos":["sony/audio-visual-seld-dcase2023"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/perception-test-a-diagnostic-benchmark-for-2","slug":"perception-test-a-diagnostic-benchmark-for-2","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","date":"2023-05-23","arxiv_id":"2305.13786","repositories_listed":1,"syntology":null},{"url":"/paper/ad-yolo-you-look-only-once-in-training","slug":"ad-yolo-you-look-only-once-in-training","title":"AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection","date":"2023-03-28","arxiv_id":"2303.15703","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ad-yolo-you-look-only-once-in-training#ran","syntology_url":"https://syntology.ai/paper/2303.15703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15703"}},"official":{"repos":["sadPororo/AD-YOLO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-synapse-threshold-synergistic-learning","slug":"a-synapse-threshold-synergistic-learning","title":"A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks","date":"2022-06-10","arxiv_id":"2206.06129","repositories_listed":1,"syntology":null},{"url":"/paper/dual-quaternion-ambisonics-array-for-six","slug":"dual-quaternion-ambisonics-array-for-six","title":"Dual Quaternion Ambisonics Array for Six-Degree-of-Freedom Acoustic Representation","date":"2022-04-04","arxiv_id":"2204.01851","repositories_listed":1,"syntology":null},{"url":"/paper/filler-word-detection-and-classification-a","slug":"filler-word-detection-and-classification-a","title":"Filler Word Detection and Classification: A Dataset and Benchmark","date":"2022-03-28","arxiv_id":"2203.15135","repositories_listed":1,"syntology":null},{"url":"/paper/l3das22-challenge-learning-3d-audio-sources","slug":"l3das22-challenge-learning-3d-audio-sources","title":"L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment","date":"2022-02-21","arxiv_id":"2202.10372","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/l3das22-challenge-learning-3d-audio-sources#ran","syntology_url":"https://syntology.ai/paper/2202.10372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10372"}},"official":{"repos":["l3das/l3das22"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/echo-aware-adaptation-of-sound-event","slug":"echo-aware-adaptation-of-sound-event","title":"Echo-aware Adaptation of Sound Event Localization and Detection in Unknown Environments","date":"2022-02-18","arxiv_id":"2202.09121","repositories_listed":1,"syntology":null},{"url":"/paper/wearable-seld-dataset-dataset-for-sound-event","slug":"wearable-seld-dataset-dataset-for-sound-event","title":"Wearable SELD dataset: Dataset for sound event localization and detection using wearable devices around head","date":"2022-02-17","arxiv_id":"2202.08458","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-mixup-directional-loudness","slug":"spatial-mixup-directional-loudness","title":"Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection","date":"2021-10-12","arxiv_id":"2110.06126","repositories_listed":1,"syntology":null},{"url":"/paper/salsa-spatial-cue-augmented-log-spectrogram","slug":"salsa-spatial-cue-augmented-log-spectrogram","title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","date":"2021-10-01","arxiv_id":"2110.00275","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-sound-event-localization-and","slug":"what-makes-sound-event-localization-and","title":"What Makes Sound Event Localization and Detection Difficult? Insights from Error Analysis","date":"2021-07-22","arxiv_id":"2107.10469","repositories_listed":1,"syntology":null},{"url":"/paper/dcase-2021-task-3-spectrotemporally-aligned","slug":"dcase-2021-task-3-spectrotemporally-aligned","title":"DCASE 2021 Task 3: Spectrotemporally-aligned Features for Polyphonic Sound Event Localization and Detection","date":"2021-06-29","arxiv_id":"2106.15190","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-of-dynamic-reverberant-sound-scenes","slug":"a-dataset-of-dynamic-reverberant-sound-scenes","title":"A Dataset of Dynamic Reverberant Sound Scenes with Directional Interferers for Sound Event Localization and Detection","date":"2021-06-13","arxiv_id":"2106.06999","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-of-dynamic-reverberant-sound-scenes#ran","syntology_url":"https://syntology.ai/paper/2106.06999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06999"}},"official":{"repos":["sharathadavanne/seld-dcase2021"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-hybrid-parametric-deep-learning-approach","slug":"a-hybrid-parametric-deep-learning-approach","title":"A hybrid parametric-deep learning approach for sound event localization and detection","date":"2019-08-27","arxiv_id":"1908.10133","repositories_listed":1,"syntology":null},{"url":null,"slug":"spatial-and-semantic-embedding-integration","title":"Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos","date":"2025-07-07","arxiv_id":"2507.04845","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereo-sound-event-localization-and-detection","title":"Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling","date":"2025-06-16","arxiv_id":"2506.13455","repositories_listed":0,"syntology":null},{"url":null,"slug":"cst-former-multidimensional-attention-based","title":"CST-former: Multidimensional Attention-based Transformer for Sound Event Localization and Detection in Real Scenes","date":"2025-04-17","arxiv_id":"2504.12870","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-experimental-study-on-joint-modeling-for","title":"An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation","date":"2025-01-18","arxiv_id":"2501.10755","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-for-sound-event","title":"Class-Incremental Learning for Sound Event Localization and Detection","date":"2024-11-19","arxiv_id":"2411.12830","repositories_listed":0,"syntology":null},{"url":null,"slug":"doa-aware-audio-visual-self-supervised","title":"DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection","date":"2024-10-30","arxiv_id":"2410.22803","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-reverberation-and-visual-depth","title":"Leveraging Reverberation and Visual Depth Cues for Sound Event Localization and Detection with Distance Estimation","date":"2024-10-29","arxiv_id":"2410.22271","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-spatially-aware-language-and-audio","title":"Learning Spatially-Aware Language and Audio Embeddings","date":"2024-09-17","arxiv_id":"2409.11369","repositories_listed":0,"syntology":null},{"url":null,"slug":"seld-mamba-selective-state-space-model-for","title":"SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation","date":"2024-08-09","arxiv_id":"2408.05057","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeeze-and-excite-resnet-conformers-for","title":"Squeeze-and-Excite ResNet-Conformers for Sound Event Localization, Detection, and Distance Estimation for DCASE 2024 Challenge","date":"2024-07-12","arxiv_id":"2407.09021","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":"exploring-audio-visual-information-fusion-for","title":"Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios","date":"2024-06-21","arxiv_id":"2406.15160","repositories_listed":0,"syntology":null},{"url":null,"slug":"6dof-seld-sound-event-localization-and","title":"6DoF SELD: Sound Event Localization and Detection Using Microphones and Motion Tracking Sensors on self-motioning human","date":"2024-03-04","arxiv_id":"2403.01670","repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-the-l3das23-challenge-on-audio","title":"Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality","date":"2024-02-14","arxiv_id":"2402.09245","repositories_listed":0,"syntology":null},{"url":null,"slug":"bat-learning-to-reason-about-spatial-sounds","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01591","repositories_listed":0,"syntology":null},{"url":null,"slug":"cst-former-transformer-with-channel-spectro","title":"CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection","date":"2023-12-20","arxiv_id":"2312.12821","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":"swg-former-sliding-window-graph-convolutional","title":"SwG-former: A Sliding-Window Graph Convolutional Network for Simultaneous Spatial-Temporal Information Extraction in Sound Event Localization and Detection","date":"2023-10-21","arxiv_id":"2310.14016","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-seld-meta-learning-for-fast-adaptation","title":"META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection","date":"2023-08-17","arxiv_id":"2308.08847","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-kernel-convolution-network-with-scene","title":"Dynamic Kernel Convolution Network with Scene-dedicate Training for Sound Event Localization and Detection","date":"2023-07-17","arxiv_id":"2307.08239","repositories_listed":0,"syntology":null},{"url":null,"slug":"divided-spectro-temporal-attention-for-sound","title":"Divided spectro-temporal attention for sound event localization and detection in real scenes for DCASE2023 challenge","date":"2023-06-05","arxiv_id":"2306.02591","repositories_listed":0,"syntology":null},{"url":null,"slug":"coloc-conditioned-localizer-and-classifier","title":"CoLoC: Conditioned Localizer and Classifier for Sound Event Localization and Detection","date":"2022-10-25","arxiv_id":"2210.13932","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-and-squeeze-and-excitation","title":"Data Augmentation and Squeeze-and-Excitation Network on Multiple Dimension for Sound Event Localization and Detection in Real Scenes","date":"2022-06-24","arxiv_id":"2206.12059","repositories_listed":0,"syntology":null},{"url":null,"slug":"locate-this-not-that-class-conditioned-sound","title":"Locate This, Not That: Class-Conditioned Sound Event DOA Estimation","date":"2022-03-08","arxiv_id":"2203.04197","repositories_listed":0,"syntology":null},{"url":null,"slug":"task3-dcase2021-challenge-sound-event","title":"TASK3 DCASE2021 Challenge: Sound event localization and detection using squeeze-excitation residual CNNs","date":"2021-07-30","arxiv_id":"2107.14561","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-microphone-array-speech-detection-and","title":"Mobile Microphone Array Speech Detection and Localization in Diverse Everyday Environments","date":"2021-06-28","arxiv_id":"2106.14787","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-of-accdoa-and-einv2-based-systems","title":"Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection","date":"2021-06-21","arxiv_id":"2106.10806","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sequence-matching-network-for-polyphonic","title":"A Sequence Matching Network for Polyphonic Sound Event Localization and Detection","date":"2020-02-14","arxiv_id":"2002.05865","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-event-localization-based-on-sound","title":"Sound Event Localization based on Sound Intensity Vector Refined By DNN-Based Denoising and Source Separation","date":"2020-02-14","arxiv_id":"2002.05994","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-source-detection-localization-and","title":"Sound source detection, localization and classification using consecutive ensemble of CRNN models","date":"2019-08-02","arxiv_id":"1908.00766","repositories_listed":0,"syntology":null}],"syntology_records":8,"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-event-localization-and-detection/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":"ran","page":1,"of":1,"url":"/task/sound-event-localization-and-detection/papers/ran/1","json":"/task/sound-event-localization-and-detection/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":"3eb616341bb5f217f97ce44bc258a104918fc1aaef07959133669a652af27947","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}