{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T3VIWWIMJDV2F2Z5GFWB5Q2WR4","short_pith_number":"pith:T3VIWWIM","schema_version":"1.0","canonical_sha256":"9eea8b590c48eba2eb3d316c1ec3568f03977a7b04ee1fcac0b061a1e1749d1e","source":{"kind":"arxiv","id":"2109.01989","version":1},"attestation_state":"computed","paper":{"title":"The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Miao Zhao, Min Liu, Minqiang Xu, Yufeng Ma","submitted_at":"2021-09-05T04:07:05Z","abstract_excerpt":"This report describes our submission to the track 1 and track 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC 2021). Both track 1 and track 2 share the same speaker verification system, which only uses VoxCeleb2-dev as our training set. This report explores several parts, including data augmentation, network structures, domain-based large margin fine-tuning, and back-end refinement. Our system is a fusion of 9 models and achieves first place in these two tracks of VoxSRC 2021. The minDCF of our submission is 0.1034, and the corresponding EER is 1.8460%."},"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":"2109.01989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-09-05T04:07:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"717b08ad6e61bc00adfdc13ed6f2d14dd542a2589d715255f127b3762832f876","abstract_canon_sha256":"7fa7b059a809d8cc2e2406076185f15d5166315a696bf89dd54c1c5b70d11564"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:37.156410Z","signature_b64":"6u6GXOZq7bIr2uu3r/sDGVTA4pvxnvEDuQpZt7cd5f0ZtsMsQyMk6ZE9ogjqt6lc1hYgW+//aiblknXGGzF6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eea8b590c48eba2eb3d316c1ec3568f03977a7b04ee1fcac0b061a1e1749d1e","last_reissued_at":"2026-07-05T03:11:37.155926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:37.155926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Miao Zhao, Min Liu, Minqiang Xu, Yufeng Ma","submitted_at":"2021-09-05T04:07:05Z","abstract_excerpt":"This report describes our submission to the track 1 and track 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC 2021). Both track 1 and track 2 share the same speaker verification system, which only uses VoxCeleb2-dev as our training set. This report explores several parts, including data augmentation, network structures, domain-based large margin fine-tuning, and back-end refinement. Our system is a fusion of 9 models and achieves first place in these two tracks of VoxSRC 2021. The minDCF of our submission is 0.1034, and the corresponding EER is 1.8460%."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01989","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/2109.01989/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":"2109.01989","created_at":"2026-07-05T03:11:37.155986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01989v1","created_at":"2026-07-05T03:11:37.155986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01989","created_at":"2026-07-05T03:11:37.155986+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3VIWWIMJDV2","created_at":"2026-07-05T03:11:37.155986+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3VIWWIMJDV2F2Z5","created_at":"2026-07-05T03:11:37.155986+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3VIWWIM","created_at":"2026-07-05T03:11:37.155986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11514","citing_title":"CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29335","citing_title":"AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4","json":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4.json","graph_json":"https://pith.science/api/pith-number/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/graph.json","events_json":"https://pith.science/api/pith-number/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/events.json","paper":"https://pith.science/paper/T3VIWWIM"},"agent_actions":{"view_html":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4","download_json":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4.json","view_paper":"https://pith.science/paper/T3VIWWIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01989&json=true","fetch_graph":"https://pith.science/api/pith-number/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/graph.json","fetch_events":"https://pith.science/api/pith-number/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/action/storage_attestation","attest_author":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/action/author_attestation","sign_citation":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/action/citation_signature","submit_replication":"https://pith.science/pith/T3VIWWIMJDV2F2Z5GFWB5Q2WR4/action/replication_record"}},"created_at":"2026-07-05T03:11:37.155986+00:00","updated_at":"2026-07-05T03:11:37.155986+00:00"}