{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DCSAC6H6EH77XYWXIGAGLPI4RI","short_pith_number":"pith:DCSAC6H6","schema_version":"1.0","canonical_sha256":"18a40178fe21fffbe2d7418065bd1c8a36326c6a50b97abc98b395d4b416eac6","source":{"kind":"arxiv","id":"2104.01466","version":1},"attestation_state":"computed","paper":{"title":"ECAPA-TDNN Embeddings for Speaker Diarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Brecht Desplanques, Fran\\c{c}ois Grondin, Hwidong Na, Jenthe Thienpondt, Mirco Ravanelli, Nauman Dawalatabad","submitted_at":"2021-04-03T19:37:51Z","abstract_excerpt":"Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of modern diarization systems. Recently, some improvements over the standard TDNN architecture used for x-vectors have been proposed. The ECAPA-TDNN model, for instance, has shown impressive performance in the speaker verification domain, thanks to a carefully designed neural model.\n  In this work, we extend, for the first time, the use of the ECAPA-TDNN "},"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":"2104.01466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T19:37:51Z","cross_cats_sorted":[],"title_canon_sha256":"0efa6dad405eb299e509fa4579d7c2aaa3ad6f4ec48666e39c16a7cbbc765290","abstract_canon_sha256":"9148d5bc3f07331be7a56b1603c97d28ec9eaf1a17bde5ce7f620d06b653d4bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:26.490349Z","signature_b64":"ZRAo8IDnaCwVZ9KuDIHOYke9yxIozroxyw1dJhSHvyqYUqg5hUSyyInOh/iSezCCuZn/0c1ixobclFg/pna2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18a40178fe21fffbe2d7418065bd1c8a36326c6a50b97abc98b395d4b416eac6","last_reissued_at":"2026-07-05T03:13:26.489926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:26.489926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECAPA-TDNN Embeddings for Speaker Diarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Brecht Desplanques, Fran\\c{c}ois Grondin, Hwidong Na, Jenthe Thienpondt, Mirco Ravanelli, Nauman Dawalatabad","submitted_at":"2021-04-03T19:37:51Z","abstract_excerpt":"Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of modern diarization systems. Recently, some improvements over the standard TDNN architecture used for x-vectors have been proposed. The ECAPA-TDNN model, for instance, has shown impressive performance in the speaker verification domain, thanks to a carefully designed neural model.\n  In this work, we extend, for the first time, the use of the ECAPA-TDNN "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01466","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.01466/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":"2104.01466","created_at":"2026-07-05T03:13:26.489981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01466v1","created_at":"2026-07-05T03:13:26.489981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01466","created_at":"2026-07-05T03:13:26.489981+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCSAC6H6EH77","created_at":"2026-07-05T03:13:26.489981+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCSAC6H6EH77XYWX","created_at":"2026-07-05T03:13:26.489981+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCSAC6H6","created_at":"2026-07-05T03:13:26.489981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI","json":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI.json","graph_json":"https://pith.science/api/pith-number/DCSAC6H6EH77XYWXIGAGLPI4RI/graph.json","events_json":"https://pith.science/api/pith-number/DCSAC6H6EH77XYWXIGAGLPI4RI/events.json","paper":"https://pith.science/paper/DCSAC6H6"},"agent_actions":{"view_html":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI","download_json":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI.json","view_paper":"https://pith.science/paper/DCSAC6H6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01466&json=true","fetch_graph":"https://pith.science/api/pith-number/DCSAC6H6EH77XYWXIGAGLPI4RI/graph.json","fetch_events":"https://pith.science/api/pith-number/DCSAC6H6EH77XYWXIGAGLPI4RI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI/action/storage_attestation","attest_author":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI/action/author_attestation","sign_citation":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI/action/citation_signature","submit_replication":"https://pith.science/pith/DCSAC6H6EH77XYWXIGAGLPI4RI/action/replication_record"}},"created_at":"2026-07-05T03:13:26.489981+00:00","updated_at":"2026-07-05T03:13:26.489981+00:00"}