{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IKS6HIB7TSYFOEZ7O3IID74DX2","short_pith_number":"pith:IKS6HIB7","schema_version":"1.0","canonical_sha256":"42a5e3a03f9cb057133f76d081ff83beb975d6a38b4426aab63befc3055f3c19","source":{"kind":"arxiv","id":"1906.07317","version":1},"attestation_state":"computed","paper":{"title":"Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Houjun Huang, Kai Yu, Shuai Wang, Xu Xiang, Yanmin Qian","submitted_at":"2019-06-18T00:31:04Z","abstract_excerpt":"Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy loss with softmax. However, this kind of loss function does not explicitly encourage inter-class separability and intra-class compactness. As a result, the embeddings are not optimal for speaker recognition tasks. In this paper, to address this issue, three different margin based losses which not only separate classes but also demand a fixed margin between "},"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":"1906.07317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-18T00:31:04Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ac7bc430a4c7b6562790e029ad33777f9fbe9bf55956823a146751c1fbfe05c3","abstract_canon_sha256":"50d3b1096219bedc5f66bb608d184c9e4025f45d73184bc4c5f4753eb904cc10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.219640Z","signature_b64":"bjOgulSVo3e2BFkboWSjWgJDsr4R6S7fqIjZBxATgd0LhxQLm+32oCgmDP7Cuw68Gm9u7+t6oPdUdQg9Mx/kBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a5e3a03f9cb057133f76d081ff83beb975d6a38b4426aab63befc3055f3c19","last_reissued_at":"2026-05-17T23:43:08.219168Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.219168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Houjun Huang, Kai Yu, Shuai Wang, Xu Xiang, Yanmin Qian","submitted_at":"2019-06-18T00:31:04Z","abstract_excerpt":"Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy loss with softmax. However, this kind of loss function does not explicitly encourage inter-class separability and intra-class compactness. As a result, the embeddings are not optimal for speaker recognition tasks. In this paper, to address this issue, three different margin based losses which not only separate classes but also demand a fixed margin between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07317","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":""},"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":"1906.07317","created_at":"2026-05-17T23:43:08.219236+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07317v1","created_at":"2026-05-17T23:43:08.219236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07317","created_at":"2026-05-17T23:43:08.219236+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKS6HIB7TSYF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKS6HIB7TSYFOEZ7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKS6HIB7","created_at":"2026-05-18T12:33:18.533446+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/IKS6HIB7TSYFOEZ7O3IID74DX2","json":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2.json","graph_json":"https://pith.science/api/pith-number/IKS6HIB7TSYFOEZ7O3IID74DX2/graph.json","events_json":"https://pith.science/api/pith-number/IKS6HIB7TSYFOEZ7O3IID74DX2/events.json","paper":"https://pith.science/paper/IKS6HIB7"},"agent_actions":{"view_html":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2","download_json":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2.json","view_paper":"https://pith.science/paper/IKS6HIB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07317&json=true","fetch_graph":"https://pith.science/api/pith-number/IKS6HIB7TSYFOEZ7O3IID74DX2/graph.json","fetch_events":"https://pith.science/api/pith-number/IKS6HIB7TSYFOEZ7O3IID74DX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2/action/storage_attestation","attest_author":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2/action/author_attestation","sign_citation":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2/action/citation_signature","submit_replication":"https://pith.science/pith/IKS6HIB7TSYFOEZ7O3IID74DX2/action/replication_record"}},"created_at":"2026-05-17T23:43:08.219236+00:00","updated_at":"2026-05-17T23:43:08.219236+00:00"}