{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UT7RJQU3TROQVUPIGINLNJNE3M","short_pith_number":"pith:UT7RJQU3","schema_version":"1.0","canonical_sha256":"a4ff14c29b9c5d0ad1e8321ab6a5a4db02cb484af3d8a5281e79f3d2b835cdf8","source":{"kind":"arxiv","id":"2409.10791","version":2},"attestation_state":"computed","paper":{"title":"Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Jee-weon Jung, Li-Wei Chen, Shinji Watanabe, Stephen Shum, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2024-09-16T23:53:57Z","abstract_excerpt":"Iterative self-training, or iterative pseudo-labeling (IPL) -- using an improved model from the current iteration to provide pseudo-labels for the next iteration -- has proven to be a powerful approach to enhance the quality of speaker representations. Recent applications of IPL in unsupervised speaker recognition start with representations extracted from very elaborate self-supervised methods (e.g., DINO). However, training such strong self-supervised models is not straightforward (they require hyper-parameter tuning and may not generalize to out-of-domain data) and, moreover, may not be need"},"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":"2409.10791","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:53:57Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e6649ef1a043938f4b56f0e523facdc70ca9b93458d7ae895bf0669e2b20e510","abstract_canon_sha256":"d174a0e8246585508d1e56d03603f76515bac1fb40a4e2fadf7d6b5e337d2a39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:24.463780Z","signature_b64":"qz8VKbAAnYzEaac1yYhWe9/anhIZXnCL8/Nj1KFpaB4W0pGI4KFaSnM64ZZmpe3bVPnMZJyurxt782yAWdsqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ff14c29b9c5d0ad1e8321ab6a5a4db02cb484af3d8a5281e79f3d2b835cdf8","last_reissued_at":"2026-07-05T10:02:24.463292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:24.463292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Jee-weon Jung, Li-Wei Chen, Shinji Watanabe, Stephen Shum, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2024-09-16T23:53:57Z","abstract_excerpt":"Iterative self-training, or iterative pseudo-labeling (IPL) -- using an improved model from the current iteration to provide pseudo-labels for the next iteration -- has proven to be a powerful approach to enhance the quality of speaker representations. Recent applications of IPL in unsupervised speaker recognition start with representations extracted from very elaborate self-supervised methods (e.g., DINO). However, training such strong self-supervised models is not straightforward (they require hyper-parameter tuning and may not generalize to out-of-domain data) and, moreover, may not be need"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10791","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/2409.10791/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":"2409.10791","created_at":"2026-07-05T10:02:24.463360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10791v2","created_at":"2026-07-05T10:02:24.463360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10791","created_at":"2026-07-05T10:02:24.463360+00:00"},{"alias_kind":"pith_short_12","alias_value":"UT7RJQU3TROQ","created_at":"2026-07-05T10:02:24.463360+00:00"},{"alias_kind":"pith_short_16","alias_value":"UT7RJQU3TROQVUPI","created_at":"2026-07-05T10:02:24.463360+00:00"},{"alias_kind":"pith_short_8","alias_value":"UT7RJQU3","created_at":"2026-07-05T10:02:24.463360+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/UT7RJQU3TROQVUPIGINLNJNE3M","json":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M.json","graph_json":"https://pith.science/api/pith-number/UT7RJQU3TROQVUPIGINLNJNE3M/graph.json","events_json":"https://pith.science/api/pith-number/UT7RJQU3TROQVUPIGINLNJNE3M/events.json","paper":"https://pith.science/paper/UT7RJQU3"},"agent_actions":{"view_html":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M","download_json":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M.json","view_paper":"https://pith.science/paper/UT7RJQU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10791&json=true","fetch_graph":"https://pith.science/api/pith-number/UT7RJQU3TROQVUPIGINLNJNE3M/graph.json","fetch_events":"https://pith.science/api/pith-number/UT7RJQU3TROQVUPIGINLNJNE3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M/action/storage_attestation","attest_author":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M/action/author_attestation","sign_citation":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M/action/citation_signature","submit_replication":"https://pith.science/pith/UT7RJQU3TROQVUPIGINLNJNE3M/action/replication_record"}},"created_at":"2026-07-05T10:02:24.463360+00:00","updated_at":"2026-07-05T10:02:24.463360+00:00"}