{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UORIPP7DXKXEB6WDSTJAPKN6NS","short_pith_number":"pith:UORIPP7D","schema_version":"1.0","canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","source":{"kind":"arxiv","id":"2501.00114","version":1},"attestation_state":"computed","paper":{"title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Polok, Bolaji Yusuf, Dominik Klement, Federico Landini, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Martin Kocour, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2024-12-30T19:24:15Z","abstract_excerpt":"Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose Diarization-Conditioned Whisper (DiCoW), a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information. DiCoW extends the pre-trained Whisper model by integrating diarization labels directly, eliminating reliance on speaker embeddings and reducing the need for extensive speaker-specific training data. Our meth"},"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":"2501.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"484ece3d6ef9ecba35788d3bdc08d7749bdd66b147757f03e3b75869ac7bc355","abstract_canon_sha256":"bc596f9135221d85a3479adf8c8effc4bf2de248d0db54bbcd1b7fe0672bd94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:39.301459Z","signature_b64":"oUNtm3uTzvwtxbI3Z3KnjwXyFrECNdBAyD10OQiof7zsveqSqwFUIT4Kx5268igSrnx6c3zGAdPH/c98E8uaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","last_reissued_at":"2026-07-05T09:55:39.300913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:39.300913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Polok, Bolaji Yusuf, Dominik Klement, Federico Landini, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Martin Kocour, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2024-12-30T19:24:15Z","abstract_excerpt":"Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose Diarization-Conditioned Whisper (DiCoW), a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information. DiCoW extends the pre-trained Whisper model by integrating diarization labels directly, eliminating reliance on speaker embeddings and reducing the need for extensive speaker-specific training data. Our meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00114","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/2501.00114/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":"2501.00114","created_at":"2026-07-05T09:55:39.301005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00114v1","created_at":"2026-07-05T09:55:39.301005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00114","created_at":"2026-07-05T09:55:39.301005+00:00"},{"alias_kind":"pith_short_12","alias_value":"UORIPP7DXKXE","created_at":"2026-07-05T09:55:39.301005+00:00"},{"alias_kind":"pith_short_16","alias_value":"UORIPP7DXKXEB6WD","created_at":"2026-07-05T09:55:39.301005+00:00"},{"alias_kind":"pith_short_8","alias_value":"UORIPP7D","created_at":"2026-07-05T09:55:39.301005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05609","citing_title":"MMW: Side Talk Rejection Multi-Microphone Whisper on Smart Glasses","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS","json":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS.json","graph_json":"https://pith.science/api/pith-number/UORIPP7DXKXEB6WDSTJAPKN6NS/graph.json","events_json":"https://pith.science/api/pith-number/UORIPP7DXKXEB6WDSTJAPKN6NS/events.json","paper":"https://pith.science/paper/UORIPP7D"},"agent_actions":{"view_html":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS","download_json":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS.json","view_paper":"https://pith.science/paper/UORIPP7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/UORIPP7DXKXEB6WDSTJAPKN6NS/graph.json","fetch_events":"https://pith.science/api/pith-number/UORIPP7DXKXEB6WDSTJAPKN6NS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/action/storage_attestation","attest_author":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/action/author_attestation","sign_citation":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/action/citation_signature","submit_replication":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/action/replication_record"}},"created_at":"2026-07-05T09:55:39.301005+00:00","updated_at":"2026-07-05T09:55:39.301005+00:00"}