{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZHQ7ZTBA33VQJHSKW3FHG3IK4U","short_pith_number":"pith:ZHQ7ZTBA","schema_version":"1.0","canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","source":{"kind":"arxiv","id":"2003.12222","version":6},"attestation_state":"computed","paper":{"title":"Voice activity detection in the wild via weakly supervised sound event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Yefei Chen","submitted_at":"2020-03-27T03:47:12Z","abstract_excerpt":"Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains unpredictable noise types, hence frame-level label prediction is difficult, which is required for traditional supervised VAD training. In contrast, we propose a general-purpose VAD (GPVAD) framework, which can be easily trained from noisy data in a weakly supervised fashion, requiring only clip-level labels. We proposed two GPVAD models, one full (GPV-F), trained on "},"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":"2003.12222","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a34ecf5103a31966d91ff11f300b1be165a25e141d03ece29c3f4f43ae222ca5","abstract_canon_sha256":"5809fed3dde2d17526c3c76302a0949982d539ea7f8e5a09726105845d9116fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:22.285176Z","signature_b64":"KNW11ieK0VEvpccn8aQVx0VjdGecJHobZX9/oGEuoXdyanAXLFmQovmf+PTzS70/PqIomijb/sI9l06fsd9SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","last_reissued_at":"2026-07-05T01:27:22.284474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:22.284474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voice activity detection in the wild via weakly supervised sound event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Yefei Chen","submitted_at":"2020-03-27T03:47:12Z","abstract_excerpt":"Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains unpredictable noise types, hence frame-level label prediction is difficult, which is required for traditional supervised VAD training. In contrast, we propose a general-purpose VAD (GPVAD) framework, which can be easily trained from noisy data in a weakly supervised fashion, requiring only clip-level labels. We proposed two GPVAD models, one full (GPV-F), trained on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12222","kind":"arxiv","version":6},"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/2003.12222/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":"2003.12222","created_at":"2026-07-05T01:27:22.284543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12222v6","created_at":"2026-07-05T01:27:22.284543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12222","created_at":"2026-07-05T01:27:22.284543+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHQ7ZTBA33VQ","created_at":"2026-07-05T01:27:22.284543+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHQ7ZTBA33VQJHSK","created_at":"2026-07-05T01:27:22.284543+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHQ7ZTBA","created_at":"2026-07-05T01:27:22.284543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01427","citing_title":"PackingGPT: 3D Packing Agent for Real Furniture in Last-Mile Delivery","ref_index":2003,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U","json":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U.json","graph_json":"https://pith.science/api/pith-number/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/graph.json","events_json":"https://pith.science/api/pith-number/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/events.json","paper":"https://pith.science/paper/ZHQ7ZTBA"},"agent_actions":{"view_html":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U","download_json":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U.json","view_paper":"https://pith.science/paper/ZHQ7ZTBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12222&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/action/storage_attestation","attest_author":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/action/author_attestation","sign_citation":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/action/citation_signature","submit_replication":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/action/replication_record"}},"created_at":"2026-07-05T01:27:22.284543+00:00","updated_at":"2026-07-05T01:27:22.284543+00:00"}