{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F7SBGMZSU4JAT5NHCD3DHYML7V","short_pith_number":"pith:F7SBGMZS","schema_version":"1.0","canonical_sha256":"2fe4133332a71209f5a710f633e18bfd645bf9261e3724dc31a753a97daca14f","source":{"kind":"arxiv","id":"2103.15421","version":2},"attestation_state":"computed","paper":{"title":"Improved Meta-Learning Training for Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Gu, Wu Guo, Yafeng Chen","submitted_at":"2021-03-29T08:37:27Z","abstract_excerpt":"Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly trained with the conventional cross entropy loss and prototypical networks (PN) loss. Then, inspired by speaker adaptive training in speech recognition, additional transformation coefficients are trained with only the PN loss. The transformation coefficients are used to modify the original backbone embedding network in the x-vector extraction process. Furthermor"},"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":"2103.15421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-29T08:37:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c2016b28244c3075d2cf9e4755106913dbf122ca77f114713839ec39842895cc","abstract_canon_sha256":"3bdf0905e5590c4fd4851be1e4f5fbb4df75215ef25af03c091c494a6891a399"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:09.434035Z","signature_b64":"/g7efgC5iwF5cR1IJIGCxaT/r9d/+2Osn8b5Q79WIJhCicNDNSGXVuHn4TQ8pcXqoYphwoIjEMFZnb+LdKYVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe4133332a71209f5a710f633e18bfd645bf9261e3724dc31a753a97daca14f","last_reissued_at":"2026-07-05T06:37:09.433695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:09.433695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Meta-Learning Training for Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Gu, Wu Guo, Yafeng Chen","submitted_at":"2021-03-29T08:37:27Z","abstract_excerpt":"Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly trained with the conventional cross entropy loss and prototypical networks (PN) loss. Then, inspired by speaker adaptive training in speech recognition, additional transformation coefficients are trained with only the PN loss. The transformation coefficients are used to modify the original backbone embedding network in the x-vector extraction process. Furthermor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15421","kind":"arxiv","version":2},"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/2103.15421/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":"2103.15421","created_at":"2026-07-05T06:37:09.433751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15421v2","created_at":"2026-07-05T06:37:09.433751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15421","created_at":"2026-07-05T06:37:09.433751+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7SBGMZSU4JA","created_at":"2026-07-05T06:37:09.433751+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7SBGMZSU4JAT5NH","created_at":"2026-07-05T06:37:09.433751+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7SBGMZS","created_at":"2026-07-05T06:37:09.433751+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/F7SBGMZSU4JAT5NHCD3DHYML7V","json":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V.json","graph_json":"https://pith.science/api/pith-number/F7SBGMZSU4JAT5NHCD3DHYML7V/graph.json","events_json":"https://pith.science/api/pith-number/F7SBGMZSU4JAT5NHCD3DHYML7V/events.json","paper":"https://pith.science/paper/F7SBGMZS"},"agent_actions":{"view_html":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V","download_json":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V.json","view_paper":"https://pith.science/paper/F7SBGMZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15421&json=true","fetch_graph":"https://pith.science/api/pith-number/F7SBGMZSU4JAT5NHCD3DHYML7V/graph.json","fetch_events":"https://pith.science/api/pith-number/F7SBGMZSU4JAT5NHCD3DHYML7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V/action/storage_attestation","attest_author":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V/action/author_attestation","sign_citation":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V/action/citation_signature","submit_replication":"https://pith.science/pith/F7SBGMZSU4JAT5NHCD3DHYML7V/action/replication_record"}},"created_at":"2026-07-05T06:37:09.433751+00:00","updated_at":"2026-07-05T06:37:09.433751+00:00"}