{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N7EXEYW5ET772YGBOTN6GI3F46","short_pith_number":"pith:N7EXEYW5","schema_version":"1.0","canonical_sha256":"6fc97262dd24fffd60c174dbe32365e7817d2897e6e88ad3ebd5a00bab45a8ba","source":{"kind":"arxiv","id":"1902.07821","version":1},"attestation_state":"computed","paper":{"title":"Deep Speaker Embedding Learning with Multi-Level Pooling for Text-Independent Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Guohong Ding, Jing Huang, Xiaodong He, Yun Tang","submitted_at":"2019-02-21T00:36:24Z","abstract_excerpt":"This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural networks (LSTM) to generate complementary speaker information at different levels; (2) a multi-level pooling strategy to collect speaker information from both TDNN and LSTM layers; (3) a regularization scheme on the speaker embedding extraction layer to make the extracted embeddings suitable for the following fusion step. The synergy of these improvements are s"},"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":"1902.07821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-21T00:36:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"abdcb74622a1db0e5df66412240c643aeaf9487f6c9a2dd3b45cbff4c2c673b4","abstract_canon_sha256":"ba1981b8cbeb9c330e9ed5699e0eb5ece0bad56b2e4aab45e94ef042b4f6560e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:03.791634Z","signature_b64":"EjKjuaAL+FVw6O4taxqZXRD6V9uH8Kb/YNpFkYRtfDQHnMyKKx15OqPL/ux16p8lAKXJkS8/YroFqAxHaRaYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc97262dd24fffd60c174dbe32365e7817d2897e6e88ad3ebd5a00bab45a8ba","last_reissued_at":"2026-05-17T23:53:03.791055Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:03.791055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Speaker Embedding Learning with Multi-Level Pooling for Text-Independent Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Guohong Ding, Jing Huang, Xiaodong He, Yun Tang","submitted_at":"2019-02-21T00:36:24Z","abstract_excerpt":"This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural networks (LSTM) to generate complementary speaker information at different levels; (2) a multi-level pooling strategy to collect speaker information from both TDNN and LSTM layers; (3) a regularization scheme on the speaker embedding extraction layer to make the extracted embeddings suitable for the following fusion step. The synergy of these improvements are s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07821","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":"1902.07821","created_at":"2026-05-17T23:53:03.791147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.07821v1","created_at":"2026-05-17T23:53:03.791147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07821","created_at":"2026-05-17T23:53:03.791147+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7EXEYW5ET77","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7EXEYW5ET772YGB","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7EXEYW5","created_at":"2026-05-18T12:33:24.271573+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/N7EXEYW5ET772YGBOTN6GI3F46","json":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46.json","graph_json":"https://pith.science/api/pith-number/N7EXEYW5ET772YGBOTN6GI3F46/graph.json","events_json":"https://pith.science/api/pith-number/N7EXEYW5ET772YGBOTN6GI3F46/events.json","paper":"https://pith.science/paper/N7EXEYW5"},"agent_actions":{"view_html":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46","download_json":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46.json","view_paper":"https://pith.science/paper/N7EXEYW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.07821&json=true","fetch_graph":"https://pith.science/api/pith-number/N7EXEYW5ET772YGBOTN6GI3F46/graph.json","fetch_events":"https://pith.science/api/pith-number/N7EXEYW5ET772YGBOTN6GI3F46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46/action/storage_attestation","attest_author":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46/action/author_attestation","sign_citation":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46/action/citation_signature","submit_replication":"https://pith.science/pith/N7EXEYW5ET772YGBOTN6GI3F46/action/replication_record"}},"created_at":"2026-05-17T23:53:03.791147+00:00","updated_at":"2026-05-17T23:53:03.791147+00:00"}