{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KWP3OUIV3M5MHYFP77CZ4PNYY","short_pith_number":"pith:5KWP3OUI","schema_version":"1.0","canonical_sha256":"eaacfdba88aed9d61f057ffe2cf1edc63bfce5027b73f6fc71b98287a744e565","source":{"kind":"arxiv","id":"2306.02591","version":1},"attestation_state":"computed","paper":{"title":"Divided spectro-temporal attention for sound event localization and detection in real scenes for DCASE2023 challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Byeong-Yun Ko, Jung-Woo Choi, Yusun Shul","submitted_at":"2023-06-05T04:39:34Z","abstract_excerpt":"Localizing sounds and detecting events in different room environments is a difficult task, mainly due to the wide range of reflections and reverberations. When training neural network models with sounds recorded in only a few room environments, there is a tendency for the models to become overly specialized to those specific environments, resulting in overfitting. To address this overfitting issue, we propose divided spectro-temporal attention. In comparison to the baseline method, which utilizes a convolutional recurrent neural network (CRNN) followed by a temporal multi-head self-attention l"},"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":"2306.02591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-05T04:39:34Z","cross_cats_sorted":[],"title_canon_sha256":"d4e06bacacd8b022a003a18f6cf67744484ba8997bca280283c09c396753ebef","abstract_canon_sha256":"e7ba65d3cef49be2bff141c38c1dd240c51c6836f118c2930d508294e23b96ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:19.079885Z","signature_b64":"RNCt/rVK0DnXlY8gczk5QwOYMfAn/ye7rCx90bu6OtqqxCdEMfDrKuA/+HnePvKHB3si7bMlmoE2fLvBJl/KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaacfdba88aed9d61f057ffe2cf1edc63bfce5027b73f6fc71b98287a744e565","last_reissued_at":"2026-07-05T06:17:19.079486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:19.079486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divided spectro-temporal attention for sound event localization and detection in real scenes for DCASE2023 challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Byeong-Yun Ko, Jung-Woo Choi, Yusun Shul","submitted_at":"2023-06-05T04:39:34Z","abstract_excerpt":"Localizing sounds and detecting events in different room environments is a difficult task, mainly due to the wide range of reflections and reverberations. When training neural network models with sounds recorded in only a few room environments, there is a tendency for the models to become overly specialized to those specific environments, resulting in overfitting. To address this overfitting issue, we propose divided spectro-temporal attention. In comparison to the baseline method, which utilizes a convolutional recurrent neural network (CRNN) followed by a temporal multi-head self-attention l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02591","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/2306.02591/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":"2306.02591","created_at":"2026-07-05T06:17:19.079542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02591v1","created_at":"2026-07-05T06:17:19.079542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02591","created_at":"2026-07-05T06:17:19.079542+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KWP3OUIV3M5","created_at":"2026-07-05T06:17:19.079542+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KWP3OUIV3M5MHYF","created_at":"2026-07-05T06:17:19.079542+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KWP3OUI","created_at":"2026-07-05T06:17:19.079542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22322","citing_title":"A Two-Step Learning Framework for Enhancing Sound Event Localization and Detection","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY","json":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY.json","graph_json":"https://pith.science/api/pith-number/5KWP3OUIV3M5MHYFP77CZ4PNYY/graph.json","events_json":"https://pith.science/api/pith-number/5KWP3OUIV3M5MHYFP77CZ4PNYY/events.json","paper":"https://pith.science/paper/5KWP3OUI"},"agent_actions":{"view_html":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY","download_json":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY.json","view_paper":"https://pith.science/paper/5KWP3OUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02591&json=true","fetch_graph":"https://pith.science/api/pith-number/5KWP3OUIV3M5MHYFP77CZ4PNYY/graph.json","fetch_events":"https://pith.science/api/pith-number/5KWP3OUIV3M5MHYFP77CZ4PNYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY/action/storage_attestation","attest_author":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY/action/author_attestation","sign_citation":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY/action/citation_signature","submit_replication":"https://pith.science/pith/5KWP3OUIV3M5MHYFP77CZ4PNYY/action/replication_record"}},"created_at":"2026-07-05T06:17:19.079542+00:00","updated_at":"2026-07-05T06:17:19.079542+00:00"}