{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3VCLSRDXRKZD25CVEOXF5EBLAR","short_pith_number":"pith:3VCLSRDX","schema_version":"1.0","canonical_sha256":"dd44b944778ab23d745523ae5e902b0442636193766c60b007b17b3bc98fcb38","source":{"kind":"arxiv","id":"2507.00874","version":1},"attestation_state":"computed","paper":{"title":"Improving Stereo 3D Sound Event Localization and Detection: Perceptual Features, Stereo-specific Data Augmentation, and Distance Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ee-Leng Tan, Jun-Wei Yeow, Santi Peksi, Woon-Seng Gan","submitted_at":"2025-07-01T15:37:46Z","abstract_excerpt":"This technical report presents our submission to Task 3 of the DCASE 2025 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. We address the audio-only task in this report and introduce several key contributions. First, we design perceptually-motivated input features that improve event detection, sound source localization, and distance estimation. Second, we adapt augmentation strategies specifically for the intricacies of stereo audio, including channel swapping and time-frequency masking. We also incorporate the recently proposed FilterAugment technique "},"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":"2507.00874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-01T15:37:46Z","cross_cats_sorted":[],"title_canon_sha256":"50a8fddacde0bd8bedd221e4f6c89851307e852644c330ff3f4d12cf082360f4","abstract_canon_sha256":"82fc7629a8433459979ab69292e4c313c5c238eab580ee20b404497b0db3ce15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:16.509018Z","signature_b64":"SVTqaKlxfI7pJuuKmRMuXoBwU2wo7JQmVaI3FY9DBOpO/hQokuD5+LFnur2u0fmKZUXav3Ry8JshFu/zIc3gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd44b944778ab23d745523ae5e902b0442636193766c60b007b17b3bc98fcb38","last_reissued_at":"2026-07-05T11:30:16.508499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:16.508499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Stereo 3D Sound Event Localization and Detection: Perceptual Features, Stereo-specific Data Augmentation, and Distance Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ee-Leng Tan, Jun-Wei Yeow, Santi Peksi, Woon-Seng Gan","submitted_at":"2025-07-01T15:37:46Z","abstract_excerpt":"This technical report presents our submission to Task 3 of the DCASE 2025 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. We address the audio-only task in this report and introduce several key contributions. First, we design perceptually-motivated input features that improve event detection, sound source localization, and distance estimation. Second, we adapt augmentation strategies specifically for the intricacies of stereo audio, including channel swapping and time-frequency masking. We also incorporate the recently proposed FilterAugment technique "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00874","kind":"arxiv","version":1},"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/2507.00874/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":"2507.00874","created_at":"2026-07-05T11:30:16.508580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00874v1","created_at":"2026-07-05T11:30:16.508580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00874","created_at":"2026-07-05T11:30:16.508580+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VCLSRDXRKZD","created_at":"2026-07-05T11:30:16.508580+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VCLSRDXRKZD25CV","created_at":"2026-07-05T11:30:16.508580+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VCLSRDX","created_at":"2026-07-05T11:30:16.508580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00874","citing_title":"Improving Stereo 3D Sound Event Localization and Detection: Perceptual Features, Stereo-specific Data Augmentation, and Distance Normalization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR","json":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR.json","graph_json":"https://pith.science/api/pith-number/3VCLSRDXRKZD25CVEOXF5EBLAR/graph.json","events_json":"https://pith.science/api/pith-number/3VCLSRDXRKZD25CVEOXF5EBLAR/events.json","paper":"https://pith.science/paper/3VCLSRDX"},"agent_actions":{"view_html":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR","download_json":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR.json","view_paper":"https://pith.science/paper/3VCLSRDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00874&json=true","fetch_graph":"https://pith.science/api/pith-number/3VCLSRDXRKZD25CVEOXF5EBLAR/graph.json","fetch_events":"https://pith.science/api/pith-number/3VCLSRDXRKZD25CVEOXF5EBLAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR/action/storage_attestation","attest_author":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR/action/author_attestation","sign_citation":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR/action/citation_signature","submit_replication":"https://pith.science/pith/3VCLSRDXRKZD25CVEOXF5EBLAR/action/replication_record"}},"created_at":"2026-07-05T11:30:16.508580+00:00","updated_at":"2026-07-05T11:30:16.508580+00:00"}