{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JZA4YAHZT2DCUYNTXD7EF5WYNN","short_pith_number":"pith:JZA4YAHZ","schema_version":"1.0","canonical_sha256":"4e41cc00f99e862a61b3b8fe42f6d86b5fbc9f4fa1d01df524e978a773c2268f","source":{"kind":"arxiv","id":"2109.02853","version":1},"attestation_state":"computed","paper":{"title":"The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danwei Cai, Ming Li","submitted_at":"2021-09-07T04:13:48Z","abstract_excerpt":"This report describes the submission of the DKU-DukeECE team to the self-supervision speaker verification task of the 2021 VoxCeleb Speaker Recognition Challenge (VoxSRC). Our method employs an iterative labeling framework to learn self-supervised speaker representation based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding o"},"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":"2109.02853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-09-07T04:13:48Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"10441ea8d94ffd70e21cf27003985bd3e2813e5d1c08a2186583b70d6c861b06","abstract_canon_sha256":"1fb5b5a0b67a5f2f015815865a020e5ab9e5c4cacf3d89cc6715bfcad7af6adb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:20.340765Z","signature_b64":"EIy3J43XrfTPQEz+hVl/Q5pVAGV2RnIiVh5JCf7eluVKNUvd9NPExtBOSM7pNgnAcYaHCXS9hlIFA8k/IkJlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e41cc00f99e862a61b3b8fe42f6d86b5fbc9f4fa1d01df524e978a773c2268f","last_reissued_at":"2026-07-05T03:12:20.340276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:20.340276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danwei Cai, Ming Li","submitted_at":"2021-09-07T04:13:48Z","abstract_excerpt":"This report describes the submission of the DKU-DukeECE team to the self-supervision speaker verification task of the 2021 VoxCeleb Speaker Recognition Challenge (VoxSRC). Our method employs an iterative labeling framework to learn self-supervised speaker representation based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02853","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/2109.02853/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":"2109.02853","created_at":"2026-07-05T03:12:20.340340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02853v1","created_at":"2026-07-05T03:12:20.340340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02853","created_at":"2026-07-05T03:12:20.340340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZA4YAHZT2DC","created_at":"2026-07-05T03:12:20.340340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZA4YAHZT2DCUYNT","created_at":"2026-07-05T03:12:20.340340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZA4YAHZ","created_at":"2026-07-05T03:12:20.340340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04147","citing_title":"Enhancing Self-Supervised Speaker Verification Using Similarity-Connected Graphs and GCN","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN","json":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN.json","graph_json":"https://pith.science/api/pith-number/JZA4YAHZT2DCUYNTXD7EF5WYNN/graph.json","events_json":"https://pith.science/api/pith-number/JZA4YAHZT2DCUYNTXD7EF5WYNN/events.json","paper":"https://pith.science/paper/JZA4YAHZ"},"agent_actions":{"view_html":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN","download_json":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN.json","view_paper":"https://pith.science/paper/JZA4YAHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02853&json=true","fetch_graph":"https://pith.science/api/pith-number/JZA4YAHZT2DCUYNTXD7EF5WYNN/graph.json","fetch_events":"https://pith.science/api/pith-number/JZA4YAHZT2DCUYNTXD7EF5WYNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN/action/storage_attestation","attest_author":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN/action/author_attestation","sign_citation":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN/action/citation_signature","submit_replication":"https://pith.science/pith/JZA4YAHZT2DCUYNTXD7EF5WYNN/action/replication_record"}},"created_at":"2026-07-05T03:12:20.340340+00:00","updated_at":"2026-07-05T03:12:20.340340+00:00"}