{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2ZKM4T4AEYKKEI4CFEVWXX7AS2","short_pith_number":"pith:2ZKM4T4A","schema_version":"1.0","canonical_sha256":"d654ce4f802614a22382292b6bdfe096a5d0fedb2bad7282723ebecd8f651713","source":{"kind":"arxiv","id":"2210.10985","version":2},"attestation_state":"computed","paper":{"title":"Large-scale learning of generalised representations for speaker recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Hee-Soo Heo, Hye-Jin Shim, Jaesong Lee, Jee-weon Jung, Joon Son Chung, Shinji Watanabe, Youngki Kwon","submitted_at":"2022-10-20T03:08:18Z","abstract_excerpt":"The objective of this work is to develop a speaker recognition model to be used in diverse scenarios. We hypothesise that two components should be adequately configured to build such a model. First, adequate architecture would be required. We explore several recent state-of-the-art models, including ECAPA-TDNN and MFA-Conformer, as well as other baselines. Second, a massive amount of data would be required. We investigate several new training data configurations combining a few existing datasets. The most extensive configuration includes over 87k speakers' 10.22k hours of speech. Four evaluati"},"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":"2210.10985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-20T03:08:18Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5236d41251543dcdcf8695595a5a16083760ae18b69210728506cd9a8452b9db","abstract_canon_sha256":"99a87ba0eccad233fe1ad75cb1424f5b07d29fc8ceca7ecd06a682c522866c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:59.057146Z","signature_b64":"G5Ag/6ua9ioeHM0D3qJhQj5jMbGxUXWpZt9TZyCI2bhnBRA9yMeEW35jRZnDG5H3nipH9E9tgcCS0rOLIJ7ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d654ce4f802614a22382292b6bdfe096a5d0fedb2bad7282723ebecd8f651713","last_reissued_at":"2026-07-05T05:10:59.056742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:59.056742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale learning of generalised representations for speaker recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Hee-Soo Heo, Hye-Jin Shim, Jaesong Lee, Jee-weon Jung, Joon Son Chung, Shinji Watanabe, Youngki Kwon","submitted_at":"2022-10-20T03:08:18Z","abstract_excerpt":"The objective of this work is to develop a speaker recognition model to be used in diverse scenarios. We hypothesise that two components should be adequately configured to build such a model. First, adequate architecture would be required. We explore several recent state-of-the-art models, including ECAPA-TDNN and MFA-Conformer, as well as other baselines. Second, a massive amount of data would be required. We investigate several new training data configurations combining a few existing datasets. The most extensive configuration includes over 87k speakers' 10.22k hours of speech. Four evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10985","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.10985/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":"2210.10985","created_at":"2026-07-05T05:10:59.056799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10985v2","created_at":"2026-07-05T05:10:59.056799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10985","created_at":"2026-07-05T05:10:59.056799+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZKM4T4AEYKK","created_at":"2026-07-05T05:10:59.056799+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZKM4T4AEYKKEI4C","created_at":"2026-07-05T05:10:59.056799+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZKM4T4A","created_at":"2026-07-05T05:10:59.056799+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/2ZKM4T4AEYKKEI4CFEVWXX7AS2","json":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2.json","graph_json":"https://pith.science/api/pith-number/2ZKM4T4AEYKKEI4CFEVWXX7AS2/graph.json","events_json":"https://pith.science/api/pith-number/2ZKM4T4AEYKKEI4CFEVWXX7AS2/events.json","paper":"https://pith.science/paper/2ZKM4T4A"},"agent_actions":{"view_html":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2","download_json":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2.json","view_paper":"https://pith.science/paper/2ZKM4T4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10985&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZKM4T4AEYKKEI4CFEVWXX7AS2/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZKM4T4AEYKKEI4CFEVWXX7AS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2/action/storage_attestation","attest_author":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2/action/author_attestation","sign_citation":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2/action/citation_signature","submit_replication":"https://pith.science/pith/2ZKM4T4AEYKKEI4CFEVWXX7AS2/action/replication_record"}},"created_at":"2026-07-05T05:10:59.056799+00:00","updated_at":"2026-07-05T05:10:59.056799+00:00"}