{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65NYSKLIX6EBN6HSTBOGS2SC4I","short_pith_number":"pith:65NYSKLI","schema_version":"1.0","canonical_sha256":"f75b892968bf8816f8f2985c696a42e20c34850ba49b7b83810f3b858dc81cfc","source":{"kind":"arxiv","id":"2409.09408","version":3},"attestation_state":"computed","paper":{"title":"Leveraging Self-Supervised Learning for Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Anna Silnova, Federico Landini, Jiangyu Han, Johan Rohdin, Lukas Burget, Mireia Diez","submitted_at":"2024-09-14T10:49:06Z","abstract_excerpt":"End-to-end neural diarization has evolved considerably over the past few years, but data scarcity is still a major obstacle for further improvements. Self-supervised learning methods such as WavLM have shown promising performance on several downstream tasks, but their application on speaker diarization is somehow limited. In this work, we explore using WavLM to alleviate the problem of data scarcity for neural diarization training. We use the same pipeline as Pyannote and improve the local end-to-end neural diarization with WavLM and Conformer. Experiments on far-field AMI, AISHELL-4, and AliM"},"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":"2409.09408","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-14T10:49:06Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"32bc9e92e7deda5cf15e74e2f7ce11814852de84662bfc9002b25a1c0fb5a3ef","abstract_canon_sha256":"f83ed1f6391d9fa6432266041891d722ee456853f468d2120677cbfc20d3151f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:11.738793Z","signature_b64":"BXlkqDf+H4uE4rPuAAQnHEgoCdsyfe6muZI7GB6kpaS6SH1grf8DsmVDoxlhdZEAd9iNKd7spa+cBjkZ6KSIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f75b892968bf8816f8f2985c696a42e20c34850ba49b7b83810f3b858dc81cfc","last_reissued_at":"2026-07-05T09:23:11.738396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:11.738396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Self-Supervised Learning for Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Anna Silnova, Federico Landini, Jiangyu Han, Johan Rohdin, Lukas Burget, Mireia Diez","submitted_at":"2024-09-14T10:49:06Z","abstract_excerpt":"End-to-end neural diarization has evolved considerably over the past few years, but data scarcity is still a major obstacle for further improvements. Self-supervised learning methods such as WavLM have shown promising performance on several downstream tasks, but their application on speaker diarization is somehow limited. In this work, we explore using WavLM to alleviate the problem of data scarcity for neural diarization training. We use the same pipeline as Pyannote and improve the local end-to-end neural diarization with WavLM and Conformer. Experiments on far-field AMI, AISHELL-4, and AliM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09408","kind":"arxiv","version":3},"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/2409.09408/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":"2409.09408","created_at":"2026-07-05T09:23:11.738465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09408v3","created_at":"2026-07-05T09:23:11.738465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09408","created_at":"2026-07-05T09:23:11.738465+00:00"},{"alias_kind":"pith_short_12","alias_value":"65NYSKLIX6EB","created_at":"2026-07-05T09:23:11.738465+00:00"},{"alias_kind":"pith_short_16","alias_value":"65NYSKLIX6EBN6HS","created_at":"2026-07-05T09:23:11.738465+00:00"},{"alias_kind":"pith_short_8","alias_value":"65NYSKLI","created_at":"2026-07-05T09:23:11.738465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11605","citing_title":"Dissecting the Segmentation Model of End-to-End Diarization with Vector Clustering","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I","json":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I.json","graph_json":"https://pith.science/api/pith-number/65NYSKLIX6EBN6HSTBOGS2SC4I/graph.json","events_json":"https://pith.science/api/pith-number/65NYSKLIX6EBN6HSTBOGS2SC4I/events.json","paper":"https://pith.science/paper/65NYSKLI"},"agent_actions":{"view_html":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I","download_json":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I.json","view_paper":"https://pith.science/paper/65NYSKLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09408&json=true","fetch_graph":"https://pith.science/api/pith-number/65NYSKLIX6EBN6HSTBOGS2SC4I/graph.json","fetch_events":"https://pith.science/api/pith-number/65NYSKLIX6EBN6HSTBOGS2SC4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I/action/storage_attestation","attest_author":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I/action/author_attestation","sign_citation":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I/action/citation_signature","submit_replication":"https://pith.science/pith/65NYSKLIX6EBN6HSTBOGS2SC4I/action/replication_record"}},"created_at":"2026-07-05T09:23:11.738465+00:00","updated_at":"2026-07-05T09:23:11.738465+00:00"}