{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LR4IEMHJWGZIMRV3CHQFPLSCCF","short_pith_number":"pith:LR4IEMHJ","schema_version":"1.0","canonical_sha256":"5c788230e9b1b28646bb11e057ae42114cc9c303846b4416bb6566f0b081d69f","source":{"kind":"arxiv","id":"2110.03151","version":2},"attestation_state":"computed","paper":{"title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Zhong Meng, Zhuo Chen","submitted_at":"2021-10-07T02:48:49Z","abstract_excerpt":"This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for speaker counting, multi-talker speech recognition, and speaker identification from monaural audio that contains overlapping speech. Although the E2E SA-ASR model originally does not estimate any time-related information, we show that the start and end times of each word can be estimated with sufficient accuracy from the internal state of the E2E SA-ASR by ad"},"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":"2110.03151","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T02:48:49Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"47e37d3edcd166f2fbe73dd4d6dfccca31ed711eb15dd4b4a48dcc0dac8d6368","abstract_canon_sha256":"63e98ff648efab1775fb084e240d7cb48e3e2735adfd0c0c44a651ec0c121173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:36.748479Z","signature_b64":"zkjWVuc+IXdTebd4z7+zQvlTOxhfbAKBM8H96kDl6shnqI/CZLdXCxOV33IeQ4nfvT6Rteq2VSBT4IxZxmV4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c788230e9b1b28646bb11e057ae42114cc9c303846b4416bb6566f0b081d69f","last_reissued_at":"2026-07-05T03:50:36.747901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:36.747901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Zhong Meng, Zhuo Chen","submitted_at":"2021-10-07T02:48:49Z","abstract_excerpt":"This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for speaker counting, multi-talker speech recognition, and speaker identification from monaural audio that contains overlapping speech. Although the E2E SA-ASR model originally does not estimate any time-related information, we show that the start and end times of each word can be estimated with sufficient accuracy from the internal state of the E2E SA-ASR by ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03151","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/2110.03151/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":"2110.03151","created_at":"2026-07-05T03:50:36.747973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03151v2","created_at":"2026-07-05T03:50:36.747973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03151","created_at":"2026-07-05T03:50:36.747973+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR4IEMHJWGZI","created_at":"2026-07-05T03:50:36.747973+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR4IEMHJWGZIMRV3","created_at":"2026-07-05T03:50:36.747973+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR4IEMHJ","created_at":"2026-07-05T03:50:36.747973+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/LR4IEMHJWGZIMRV3CHQFPLSCCF","json":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF.json","graph_json":"https://pith.science/api/pith-number/LR4IEMHJWGZIMRV3CHQFPLSCCF/graph.json","events_json":"https://pith.science/api/pith-number/LR4IEMHJWGZIMRV3CHQFPLSCCF/events.json","paper":"https://pith.science/paper/LR4IEMHJ"},"agent_actions":{"view_html":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF","download_json":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF.json","view_paper":"https://pith.science/paper/LR4IEMHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03151&json=true","fetch_graph":"https://pith.science/api/pith-number/LR4IEMHJWGZIMRV3CHQFPLSCCF/graph.json","fetch_events":"https://pith.science/api/pith-number/LR4IEMHJWGZIMRV3CHQFPLSCCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF/action/storage_attestation","attest_author":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF/action/author_attestation","sign_citation":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF/action/citation_signature","submit_replication":"https://pith.science/pith/LR4IEMHJWGZIMRV3CHQFPLSCCF/action/replication_record"}},"created_at":"2026-07-05T03:50:36.747973+00:00","updated_at":"2026-07-05T03:50:36.747973+00:00"}