{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2JSQM5TQUTNMZVF3OW4QX3T43P","short_pith_number":"pith:2JSQM5TQ","schema_version":"1.0","canonical_sha256":"d265067670a4daccd4bb75b90bee7cdbc09dd971eeb22c33948b6c10acf0e1a0","source":{"kind":"arxiv","id":"1806.03209","version":2},"attestation_state":"computed","paper":{"title":"Analysis of Length Normalization in End-to-End Speaker Verification System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinkun Chen, Ming Li, Weicheng Cai","submitted_at":"2018-06-08T15:09:14Z","abstract_excerpt":"The classical i-vectors and the latest end-to-end deep speaker embeddings are the two representative categories of utterance-level representations in automatic speaker verification systems. Traditionally, once i-vectors or deep speaker embeddings are extracted, we rely on an extra length normalization step to normalize the representations into unit-length hyperspace before back-end modeling. In this paper, we explore how the neural network learns length-normalized deep speaker embeddings in an end-to-end manner. To this end, we add a length normalization layer followed by a scale layer before "},"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":"1806.03209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-06-08T15:09:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6061e0f103232a19367c81365cf53552ea22a823cf2d4a451e5d36b575378078","abstract_canon_sha256":"3ed8b8daab07ae49a6b67692d55cc7bd976b74803f5510e871d5a8e61c6f83d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:43.869935Z","signature_b64":"eOJg5ywvuv8rNgtq9ARBL43o32wlrRGddzAlY8cbAAc4lXiEYsGiZ29BxbGEd8m0BFAKBUYBGoVy+RtsKH6ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d265067670a4daccd4bb75b90bee7cdbc09dd971eeb22c33948b6c10acf0e1a0","last_reissued_at":"2026-05-18T00:13:43.869248Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:43.869248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Length Normalization in End-to-End Speaker Verification System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinkun Chen, Ming Li, Weicheng Cai","submitted_at":"2018-06-08T15:09:14Z","abstract_excerpt":"The classical i-vectors and the latest end-to-end deep speaker embeddings are the two representative categories of utterance-level representations in automatic speaker verification systems. Traditionally, once i-vectors or deep speaker embeddings are extracted, we rely on an extra length normalization step to normalize the representations into unit-length hyperspace before back-end modeling. In this paper, we explore how the neural network learns length-normalized deep speaker embeddings in an end-to-end manner. To this end, we add a length normalization layer followed by a scale layer before "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03209","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":"1806.03209","created_at":"2026-05-18T00:13:43.869347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03209v2","created_at":"2026-05-18T00:13:43.869347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03209","created_at":"2026-05-18T00:13:43.869347+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JSQM5TQUTNM","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JSQM5TQUTNMZVF3","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JSQM5TQ","created_at":"2026-05-18T12:32:02.567920+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/2JSQM5TQUTNMZVF3OW4QX3T43P","json":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P.json","graph_json":"https://pith.science/api/pith-number/2JSQM5TQUTNMZVF3OW4QX3T43P/graph.json","events_json":"https://pith.science/api/pith-number/2JSQM5TQUTNMZVF3OW4QX3T43P/events.json","paper":"https://pith.science/paper/2JSQM5TQ"},"agent_actions":{"view_html":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P","download_json":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P.json","view_paper":"https://pith.science/paper/2JSQM5TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03209&json=true","fetch_graph":"https://pith.science/api/pith-number/2JSQM5TQUTNMZVF3OW4QX3T43P/graph.json","fetch_events":"https://pith.science/api/pith-number/2JSQM5TQUTNMZVF3OW4QX3T43P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P/action/storage_attestation","attest_author":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P/action/author_attestation","sign_citation":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P/action/citation_signature","submit_replication":"https://pith.science/pith/2JSQM5TQUTNMZVF3OW4QX3T43P/action/replication_record"}},"created_at":"2026-05-18T00:13:43.869347+00:00","updated_at":"2026-05-18T00:13:43.869347+00:00"}