{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OLABU6JPDIRDKVD42QTPT32Q32","short_pith_number":"pith:OLABU6JP","schema_version":"1.0","canonical_sha256":"72c01a792f1a2235547cd426f9ef50de9e227755326f08fa4818a28a7eed2415","source":{"kind":"arxiv","id":"2407.01963","version":3},"attestation_state":"computed","paper":{"title":"Towards Unsupervised Speaker Diarization System for Multilingual Telephone Calls Using Pre-trained Whisper Model and Mixture of Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Schindler, Dat Ngo, Lam Pham, Loi Khanh Nguyen, Phat Lam, Thinh Pham, Tin Nguyen, Truong Nguyen","submitted_at":"2024-07-02T05:42:32Z","abstract_excerpt":"Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these systems significantly hinder their effectiveness and scalability in multilingual settings. In this paper, we propose a cluster-based speaker diarization system designed for multilingual telephone call applications. Our proposed system supports multiple languages and eliminates the need for large-scale annotated data during training by utilizing the multilingual "},"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":"2407.01963","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-02T05:42:32Z","cross_cats_sorted":[],"title_canon_sha256":"35100bc383b30c8234a78387c4574a33e3cf49a990106d77a676671c6ab0a8c2","abstract_canon_sha256":"f9eb1465836f80ff1c22b91c8047db7c099cabf5b684417a2bac23135e7fe1a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:06.839716Z","signature_b64":"0hnrDIXQltQh4cKqN4kDenFI+d5AXliFrFcH716miC5jURxr+FR+ZMRQOLwOQbaQI3kjd5p0J2Xl0ssu/ljKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c01a792f1a2235547cd426f9ef50de9e227755326f08fa4818a28a7eed2415","last_reissued_at":"2026-07-05T09:06:06.839282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:06.839282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Unsupervised Speaker Diarization System for Multilingual Telephone Calls Using Pre-trained Whisper Model and Mixture of Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Schindler, Dat Ngo, Lam Pham, Loi Khanh Nguyen, Phat Lam, Thinh Pham, Tin Nguyen, Truong Nguyen","submitted_at":"2024-07-02T05:42:32Z","abstract_excerpt":"Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these systems significantly hinder their effectiveness and scalability in multilingual settings. In this paper, we propose a cluster-based speaker diarization system designed for multilingual telephone call applications. Our proposed system supports multiple languages and eliminates the need for large-scale annotated data during training by utilizing the multilingual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01963","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/2407.01963/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":"2407.01963","created_at":"2026-07-05T09:06:06.839343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01963v3","created_at":"2026-07-05T09:06:06.839343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01963","created_at":"2026-07-05T09:06:06.839343+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLABU6JPDIRD","created_at":"2026-07-05T09:06:06.839343+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLABU6JPDIRDKVD4","created_at":"2026-07-05T09:06:06.839343+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLABU6JP","created_at":"2026-07-05T09:06:06.839343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18582","citing_title":"Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32","json":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32.json","graph_json":"https://pith.science/api/pith-number/OLABU6JPDIRDKVD42QTPT32Q32/graph.json","events_json":"https://pith.science/api/pith-number/OLABU6JPDIRDKVD42QTPT32Q32/events.json","paper":"https://pith.science/paper/OLABU6JP"},"agent_actions":{"view_html":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32","download_json":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32.json","view_paper":"https://pith.science/paper/OLABU6JP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01963&json=true","fetch_graph":"https://pith.science/api/pith-number/OLABU6JPDIRDKVD42QTPT32Q32/graph.json","fetch_events":"https://pith.science/api/pith-number/OLABU6JPDIRDKVD42QTPT32Q32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32/action/storage_attestation","attest_author":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32/action/author_attestation","sign_citation":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32/action/citation_signature","submit_replication":"https://pith.science/pith/OLABU6JPDIRDKVD42QTPT32Q32/action/replication_record"}},"created_at":"2026-07-05T09:06:06.839343+00:00","updated_at":"2026-07-05T09:06:06.839343+00:00"}