{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HXHGAHROXIG5IRPH4WLPLPKDJW","short_pith_number":"pith:HXHGAHRO","schema_version":"1.0","canonical_sha256":"3dce601e2eba0dd445e7e596f5bd434daedcc2e856e5566e8df15c4cea30875e","source":{"kind":"arxiv","id":"2209.01802","version":2},"attestation_state":"computed","paper":{"title":"Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Feiran Yang, Jinbo Hu, Jun Yang, Mark D. Plumbley, Ming Wu, Qiuqiang Kong, Yin Cao","submitted_at":"2022-09-05T07:30:06Z","abstract_excerpt":"Sound event localization and detection (SELD) is a joint task of sound event detection and direction-of-arrival estimation. In DCASE 2022 Task 3, types of data transform from computationally generated spatial recordings to recordings of real-sound scenes. Our system submitted to the DCASE 2022 Task 3 is based on our previous proposed Event-Independent Network V2 (EINV2) with a novel data augmentation method. Our method employs EINV2 with a track-wise output format, permutation-invariant training, and a soft parameter-sharing strategy, to detect different sound events of the same class but in d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.01802","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-05T07:30:06Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f018fb3175f381f1cc5788c446b323ce79ac92697c5c0fccccc66ef05ae885e8","abstract_canon_sha256":"7b7a38a847b010fad72b3eff380edc315f847833cf657e7f0f2db1dc383c6618"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:54.089699Z","signature_b64":"6RuQfXVoIASgTsP57lkoH+S15Sp9+zb2Ptwegw9z4YWSVmIIgBt4Zk4XEH5Qj051/JGRPHJmjeGXJiPg6lZ/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dce601e2eba0dd445e7e596f5bd434daedcc2e856e5566e8df15c4cea30875e","last_reissued_at":"2026-07-05T04:55:54.089305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:54.089305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Feiran Yang, Jinbo Hu, Jun Yang, Mark D. Plumbley, Ming Wu, Qiuqiang Kong, Yin Cao","submitted_at":"2022-09-05T07:30:06Z","abstract_excerpt":"Sound event localization and detection (SELD) is a joint task of sound event detection and direction-of-arrival estimation. In DCASE 2022 Task 3, types of data transform from computationally generated spatial recordings to recordings of real-sound scenes. Our system submitted to the DCASE 2022 Task 3 is based on our previous proposed Event-Independent Network V2 (EINV2) with a novel data augmentation method. Our method employs EINV2 with a track-wise output format, permutation-invariant training, and a soft parameter-sharing strategy, to detect different sound events of the same class but in d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01802","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.01802/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.01802","created_at":"2026-07-05T04:55:54.089376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.01802v2","created_at":"2026-07-05T04:55:54.089376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01802","created_at":"2026-07-05T04:55:54.089376+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXHGAHROXIG5","created_at":"2026-07-05T04:55:54.089376+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXHGAHROXIG5IRPH","created_at":"2026-07-05T04:55:54.089376+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXHGAHRO","created_at":"2026-07-05T04:55:54.089376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02343","citing_title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW","json":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW.json","graph_json":"https://pith.science/api/pith-number/HXHGAHROXIG5IRPH4WLPLPKDJW/graph.json","events_json":"https://pith.science/api/pith-number/HXHGAHROXIG5IRPH4WLPLPKDJW/events.json","paper":"https://pith.science/paper/HXHGAHRO"},"agent_actions":{"view_html":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW","download_json":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW.json","view_paper":"https://pith.science/paper/HXHGAHRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.01802&json=true","fetch_graph":"https://pith.science/api/pith-number/HXHGAHROXIG5IRPH4WLPLPKDJW/graph.json","fetch_events":"https://pith.science/api/pith-number/HXHGAHROXIG5IRPH4WLPLPKDJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW/action/storage_attestation","attest_author":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW/action/author_attestation","sign_citation":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW/action/citation_signature","submit_replication":"https://pith.science/pith/HXHGAHROXIG5IRPH4WLPLPKDJW/action/replication_record"}},"created_at":"2026-07-05T04:55:54.089376+00:00","updated_at":"2026-07-05T04:55:54.089376+00:00"}