{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2EHLHKNCW542XQ64EKDNBOCDHC","short_pith_number":"pith:2EHLHKNC","schema_version":"1.0","canonical_sha256":"d10eb3a9a2b779abc3dc2286d0b84338996aed12cbf76c5f3345ccce804a1d3b","source":{"kind":"arxiv","id":"1806.03464","version":2},"attestation_state":"computed","paper":{"title":"Angular Softmax Loss for End-to-end Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Feng Gao, Jiasong Sun, Yutian Li, Zhijian Ou","submitted_at":"2018-06-09T11:48:03Z","abstract_excerpt":"End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extract i-vectors as speaker embeddings. In contrast, the end-to-end approach directly trains a discriminative model (often a neural network) to learn discriminative speaker embeddings; a crucial component is the training criterion. In this paper, we use angular softmax (A-softmax), which is originally proposed for face verification, as the loss function for feature learning in end-to-end speaker verification. By introduc"},"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":"1806.03464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-06-09T11:48:03Z","cross_cats_sorted":[],"title_canon_sha256":"4470f9d10b816838d7b1daffd4041c51f37b8ee01eceea65472db00e69c85b72","abstract_canon_sha256":"c627ed85bf07cf5e61997d1ab01e6bd01e0584bee283596be93eec4b073c0dd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:30.772979Z","signature_b64":"8QhPDR05FVdoqa/eM7+gvWa0PDYEKAF1dNb2ppd2oFQrN4FbqdD7TAXCh+Fvv3rvkRPltI8p5vxjh1ZaKoCIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d10eb3a9a2b779abc3dc2286d0b84338996aed12cbf76c5f3345ccce804a1d3b","last_reissued_at":"2026-05-17T23:58:30.772359Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:30.772359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Angular Softmax Loss for End-to-end Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Feng Gao, Jiasong Sun, Yutian Li, Zhijian Ou","submitted_at":"2018-06-09T11:48:03Z","abstract_excerpt":"End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extract i-vectors as speaker embeddings. In contrast, the end-to-end approach directly trains a discriminative model (often a neural network) to learn discriminative speaker embeddings; a crucial component is the training criterion. In this paper, we use angular softmax (A-softmax), which is originally proposed for face verification, as the loss function for feature learning in end-to-end speaker verification. By introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03464","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":""},"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":"1806.03464","created_at":"2026-05-17T23:58:30.772467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03464v2","created_at":"2026-05-17T23:58:30.772467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03464","created_at":"2026-05-17T23:58:30.772467+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EHLHKNCW542","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EHLHKNCW542XQ64","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EHLHKNC","created_at":"2026-05-18T12:31:59.375834+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/2EHLHKNCW542XQ64EKDNBOCDHC","json":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC.json","graph_json":"https://pith.science/api/pith-number/2EHLHKNCW542XQ64EKDNBOCDHC/graph.json","events_json":"https://pith.science/api/pith-number/2EHLHKNCW542XQ64EKDNBOCDHC/events.json","paper":"https://pith.science/paper/2EHLHKNC"},"agent_actions":{"view_html":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC","download_json":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC.json","view_paper":"https://pith.science/paper/2EHLHKNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03464&json=true","fetch_graph":"https://pith.science/api/pith-number/2EHLHKNCW542XQ64EKDNBOCDHC/graph.json","fetch_events":"https://pith.science/api/pith-number/2EHLHKNCW542XQ64EKDNBOCDHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC/action/storage_attestation","attest_author":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC/action/author_attestation","sign_citation":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC/action/citation_signature","submit_replication":"https://pith.science/pith/2EHLHKNCW542XQ64EKDNBOCDHC/action/replication_record"}},"created_at":"2026-05-17T23:58:30.772467+00:00","updated_at":"2026-05-17T23:58:30.772467+00:00"}