{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EE24MCDNK63DAKNNEROUUZVFEP","short_pith_number":"pith:EE24MCDN","schema_version":"1.0","canonical_sha256":"2135c6086d57b63029ad245d4a66a523f75f1f61c9ee39309b84c2302313ae2e","source":{"kind":"arxiv","id":"2101.02919","version":2},"attestation_state":"computed","paper":{"title":"A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Feng Ma, Hua-Xin Wu, Jia Pan, Jun Du, Qing Wang","submitted_at":"2021-01-08T08:55:37Z","abstract_excerpt":"In this paper, we propose a novel four-stage data augmentation approach to ResNet-Conformer based acoustic modeling for sound event localization and detection (SELD). First, we explore two spatial augmentation techniques, namely audio channel swapping (ACS) and multi-channel simulation (MCS), to deal with data sparsity in SELD. ACS and MDS focus on augmenting the limited training data with expanding direction of arrival (DOA) representations such that the acoustic models trained with the augmented data are robust to localization variations of acoustic sources. Next, time-domain mixing (TDM) an"},"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":"2101.02919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-01-08T08:55:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f4328562eda62530426b43ddb5ebdbdd95888b4dea70de11873471c8aea431e4","abstract_canon_sha256":"35afd3979617ebcf29670d819a93e2288563873a01182e557fdea681c81c9a4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:30.089676Z","signature_b64":"Ea9lGNubv2rV/6iSBfpva9RRatI+pOrdEBC8c2xNmNLuSat5MTudAjHXB4l/6J9EI7UGoB02CWW27miFg0OOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2135c6086d57b63029ad245d4a66a523f75f1f61c9ee39309b84c2302313ae2e","last_reissued_at":"2026-07-05T05:48:30.089276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:30.089276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Feng Ma, Hua-Xin Wu, Jia Pan, Jun Du, Qing Wang","submitted_at":"2021-01-08T08:55:37Z","abstract_excerpt":"In this paper, we propose a novel four-stage data augmentation approach to ResNet-Conformer based acoustic modeling for sound event localization and detection (SELD). First, we explore two spatial augmentation techniques, namely audio channel swapping (ACS) and multi-channel simulation (MCS), to deal with data sparsity in SELD. ACS and MDS focus on augmenting the limited training data with expanding direction of arrival (DOA) representations such that the acoustic models trained with the augmented data are robust to localization variations of acoustic sources. Next, time-domain mixing (TDM) an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02919","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/2101.02919/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":"2101.02919","created_at":"2026-07-05T05:48:30.089340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02919v2","created_at":"2026-07-05T05:48:30.089340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02919","created_at":"2026-07-05T05:48:30.089340+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE24MCDNK63D","created_at":"2026-07-05T05:48:30.089340+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE24MCDNK63DAKNN","created_at":"2026-07-05T05:48:30.089340+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE24MCDN","created_at":"2026-07-05T05:48:30.089340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09570","citing_title":"Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP","json":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP.json","graph_json":"https://pith.science/api/pith-number/EE24MCDNK63DAKNNEROUUZVFEP/graph.json","events_json":"https://pith.science/api/pith-number/EE24MCDNK63DAKNNEROUUZVFEP/events.json","paper":"https://pith.science/paper/EE24MCDN"},"agent_actions":{"view_html":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP","download_json":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP.json","view_paper":"https://pith.science/paper/EE24MCDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02919&json=true","fetch_graph":"https://pith.science/api/pith-number/EE24MCDNK63DAKNNEROUUZVFEP/graph.json","fetch_events":"https://pith.science/api/pith-number/EE24MCDNK63DAKNNEROUUZVFEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP/action/storage_attestation","attest_author":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP/action/author_attestation","sign_citation":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP/action/citation_signature","submit_replication":"https://pith.science/pith/EE24MCDNK63DAKNNEROUUZVFEP/action/replication_record"}},"created_at":"2026-07-05T05:48:30.089340+00:00","updated_at":"2026-07-05T05:48:30.089340+00:00"}