{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IK5M7STPJCYIX6Z3H2FRSZ5YM5","short_pith_number":"pith:IK5M7STP","schema_version":"1.0","canonical_sha256":"42bacfca6f48b08bfb3b3e8b1967b86775f96d68daa1b802aaf45d7497314193","source":{"kind":"arxiv","id":"2208.01928","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Yanmin Qian, Zhengyang Chen","submitted_at":"2022-08-03T09:10:13Z","abstract_excerpt":"For self-supervised speaker verification, the quality of pseudo labels decides the upper bound of the system due to the massive unreliable labels. In this work, we propose dynamic loss-gate and label correction (DLG-LC) to alleviate the performance degradation caused by unreliable estimated labels. In DLG, we adopt Gaussian Mixture Model (GMM) to dynamically model the loss distribution and use the estimated GMM to distinguish the reliable and unreliable labels automatically. Besides, to better utilize the unreliable data instead of dropping them directly, we correct the unreliable label with m"},"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":"2208.01928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-03T09:10:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"90ad21d2b0838173a301aaab978276ec99b954ad9bd10cb3eea2466679ce8774","abstract_canon_sha256":"292efad5b44bbe9dfa5286d07d3051c857b1dd48bd7260b8a01774ef165f6314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:51.450400Z","signature_b64":"izsT+RtX4Z+vS1GupLhloNkF3O2DKJLeTyxuWKvLCXFEKPf45HaRGccwu0Onx1oo9vLOjKtLvASVx1QENm1RDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42bacfca6f48b08bfb3b3e8b1967b86775f96d68daa1b802aaf45d7497314193","last_reissued_at":"2026-07-05T04:45:51.449985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:51.449985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Yanmin Qian, Zhengyang Chen","submitted_at":"2022-08-03T09:10:13Z","abstract_excerpt":"For self-supervised speaker verification, the quality of pseudo labels decides the upper bound of the system due to the massive unreliable labels. In this work, we propose dynamic loss-gate and label correction (DLG-LC) to alleviate the performance degradation caused by unreliable estimated labels. In DLG, we adopt Gaussian Mixture Model (GMM) to dynamically model the loss distribution and use the estimated GMM to distinguish the reliable and unreliable labels automatically. Besides, to better utilize the unreliable data instead of dropping them directly, we correct the unreliable label with m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01928","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/2208.01928/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":"2208.01928","created_at":"2026-07-05T04:45:51.450048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01928v1","created_at":"2026-07-05T04:45:51.450048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01928","created_at":"2026-07-05T04:45:51.450048+00:00"},{"alias_kind":"pith_short_12","alias_value":"IK5M7STPJCYI","created_at":"2026-07-05T04:45:51.450048+00:00"},{"alias_kind":"pith_short_16","alias_value":"IK5M7STPJCYIX6Z3","created_at":"2026-07-05T04:45:51.450048+00:00"},{"alias_kind":"pith_short_8","alias_value":"IK5M7STP","created_at":"2026-07-05T04:45:51.450048+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/IK5M7STPJCYIX6Z3H2FRSZ5YM5","json":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5.json","graph_json":"https://pith.science/api/pith-number/IK5M7STPJCYIX6Z3H2FRSZ5YM5/graph.json","events_json":"https://pith.science/api/pith-number/IK5M7STPJCYIX6Z3H2FRSZ5YM5/events.json","paper":"https://pith.science/paper/IK5M7STP"},"agent_actions":{"view_html":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5","download_json":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5.json","view_paper":"https://pith.science/paper/IK5M7STP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01928&json=true","fetch_graph":"https://pith.science/api/pith-number/IK5M7STPJCYIX6Z3H2FRSZ5YM5/graph.json","fetch_events":"https://pith.science/api/pith-number/IK5M7STPJCYIX6Z3H2FRSZ5YM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5/action/storage_attestation","attest_author":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5/action/author_attestation","sign_citation":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5/action/citation_signature","submit_replication":"https://pith.science/pith/IK5M7STPJCYIX6Z3H2FRSZ5YM5/action/replication_record"}},"created_at":"2026-07-05T04:45:51.450048+00:00","updated_at":"2026-07-05T04:45:51.450048+00:00"}