{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TWTGY62MDBESCVHYZYEPKYXU6F","short_pith_number":"pith:TWTGY62M","schema_version":"1.0","canonical_sha256":"9da66c7b4c18492154f8ce08f562f4f1550bb850e7b79469b8a637927386b005","source":{"kind":"arxiv","id":"2407.03661","version":3},"attestation_state":"computed","paper":{"title":"Where's That Voice Coming? Continual Learning for Sound Source Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Rohan Kumar Das, Yang Xiao","submitted_at":"2024-07-04T06:02:52Z","abstract_excerpt":"Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic acoustic conditions faces a major challenge: catastrophic forgetting. In this work, we propose an exemplar-free continual learning strategy for SSL (CL-SSL) to address such a forgetting phenomenon. CL-SSL applies task-specific sub-networks to adapt across diverse acoustic environments while retaining previously learned knowledge. It also uses a scaling mechani"},"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":"2407.03661","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-04T06:02:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e434b6b5df12b72a4d46d86466799436f924222a74a0298b3505658e1844e783","abstract_canon_sha256":"cac541cfc79bb48e02f84b0d36f798b48cfbcc4e7ada7ae4042e55e3841100ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:14.711154Z","signature_b64":"VwGi87atde4FBf9EG3Pz+2X/AFnV+gYoquKo2tu1r6e6OKNqorb/hp31Yk6EQGbXDHsMhJxswPGlUiLVp+iKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9da66c7b4c18492154f8ce08f562f4f1550bb850e7b79469b8a637927386b005","last_reissued_at":"2026-07-05T10:36:14.710513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:14.710513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where's That Voice Coming? Continual Learning for Sound Source Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Rohan Kumar Das, Yang Xiao","submitted_at":"2024-07-04T06:02:52Z","abstract_excerpt":"Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic acoustic conditions faces a major challenge: catastrophic forgetting. In this work, we propose an exemplar-free continual learning strategy for SSL (CL-SSL) to address such a forgetting phenomenon. CL-SSL applies task-specific sub-networks to adapt across diverse acoustic environments while retaining previously learned knowledge. It also uses a scaling mechani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03661","kind":"arxiv","version":3},"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/2407.03661/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":"2407.03661","created_at":"2026-07-05T10:36:14.710584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03661v3","created_at":"2026-07-05T10:36:14.710584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03661","created_at":"2026-07-05T10:36:14.710584+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWTGY62MDBES","created_at":"2026-07-05T10:36:14.710584+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWTGY62MDBESCVHY","created_at":"2026-07-05T10:36:14.710584+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWTGY62M","created_at":"2026-07-05T10:36:14.710584+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":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F","json":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F.json","graph_json":"https://pith.science/api/pith-number/TWTGY62MDBESCVHYZYEPKYXU6F/graph.json","events_json":"https://pith.science/api/pith-number/TWTGY62MDBESCVHYZYEPKYXU6F/events.json","paper":"https://pith.science/paper/TWTGY62M"},"agent_actions":{"view_html":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F","download_json":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F.json","view_paper":"https://pith.science/paper/TWTGY62M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03661&json=true","fetch_graph":"https://pith.science/api/pith-number/TWTGY62MDBESCVHYZYEPKYXU6F/graph.json","fetch_events":"https://pith.science/api/pith-number/TWTGY62MDBESCVHYZYEPKYXU6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F/action/storage_attestation","attest_author":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F/action/author_attestation","sign_citation":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F/action/citation_signature","submit_replication":"https://pith.science/pith/TWTGY62MDBESCVHYZYEPKYXU6F/action/replication_record"}},"created_at":"2026-07-05T10:36:14.710584+00:00","updated_at":"2026-07-05T10:36:14.710584+00:00"}