{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7VYSSJYKENHJFEO7RKXZLFPOOD","short_pith_number":"pith:7VYSSJYK","schema_version":"1.0","canonical_sha256":"fd7129270a234e9291df8aaf9595ee70c5f4a50f04d0184698a450f1231c438e","source":{"kind":"arxiv","id":"2110.03174","version":1},"attestation_state":"computed","paper":{"title":"Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alex Xiao, Dawei Liang, Edison Thomaz, Jonathan Shaw, Mike Seltzer, Nayan Singhal, Ozlem Kalinli, Yangyang Shi, Yun Wang","submitted_at":"2021-10-07T04:03:21Z","abstract_excerpt":"Detection of common events and scenes from audio is useful for extracting and understanding human contexts in daily life. Prior studies have shown that leveraging knowledge from a relevant domain is beneficial for a target acoustic event detection (AED) process. Inspired by the observation that many human-centered acoustic events in daily life involve voice elements, this paper investigates the potential of transferring high-level voice representations extracted from a public speaker dataset to enrich an AED pipeline. Towards this end, we develop a dual-branch neural network architecture for t"},"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":"2110.03174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T04:03:21Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"b2902ed9df5e56b4f99bf0de6187f210462c0e3c2019e5ed2c6abf9b942e6c51","abstract_canon_sha256":"c76f43042a7e2e1969875f4c2c022c49df519bb27a201d922f34949134f09c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:40.147366Z","signature_b64":"mbUYe/2nTL7Lp5JqGIKINMDB2W0arEdhylC2/n+XA+8EzwhuJMje4Dz5Vk7pCU8GslBeqcfMreCEK98KwJf4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd7129270a234e9291df8aaf9595ee70c5f4a50f04d0184698a450f1231c438e","last_reissued_at":"2026-07-05T03:20:40.146997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:40.146997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alex Xiao, Dawei Liang, Edison Thomaz, Jonathan Shaw, Mike Seltzer, Nayan Singhal, Ozlem Kalinli, Yangyang Shi, Yun Wang","submitted_at":"2021-10-07T04:03:21Z","abstract_excerpt":"Detection of common events and scenes from audio is useful for extracting and understanding human contexts in daily life. Prior studies have shown that leveraging knowledge from a relevant domain is beneficial for a target acoustic event detection (AED) process. Inspired by the observation that many human-centered acoustic events in daily life involve voice elements, this paper investigates the potential of transferring high-level voice representations extracted from a public speaker dataset to enrich an AED pipeline. Towards this end, we develop a dual-branch neural network architecture for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03174","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/2110.03174/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":"2110.03174","created_at":"2026-07-05T03:20:40.147056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03174v1","created_at":"2026-07-05T03:20:40.147056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03174","created_at":"2026-07-05T03:20:40.147056+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VYSSJYKENHJ","created_at":"2026-07-05T03:20:40.147056+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VYSSJYKENHJFEO7","created_at":"2026-07-05T03:20:40.147056+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VYSSJYK","created_at":"2026-07-05T03:20:40.147056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD","json":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD.json","graph_json":"https://pith.science/api/pith-number/7VYSSJYKENHJFEO7RKXZLFPOOD/graph.json","events_json":"https://pith.science/api/pith-number/7VYSSJYKENHJFEO7RKXZLFPOOD/events.json","paper":"https://pith.science/paper/7VYSSJYK"},"agent_actions":{"view_html":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD","download_json":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD.json","view_paper":"https://pith.science/paper/7VYSSJYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03174&json=true","fetch_graph":"https://pith.science/api/pith-number/7VYSSJYKENHJFEO7RKXZLFPOOD/graph.json","fetch_events":"https://pith.science/api/pith-number/7VYSSJYKENHJFEO7RKXZLFPOOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD/action/storage_attestation","attest_author":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD/action/author_attestation","sign_citation":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD/action/citation_signature","submit_replication":"https://pith.science/pith/7VYSSJYKENHJFEO7RKXZLFPOOD/action/replication_record"}},"created_at":"2026-07-05T03:20:40.147056+00:00","updated_at":"2026-07-05T03:20:40.147056+00:00"}