{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H6KP3FJ6PQZ6A2TBSSQGQRRBPR","short_pith_number":"pith:H6KP3FJ6","schema_version":"1.0","canonical_sha256":"3f94fd953e7c33e06a6194a06846217c5187b92411d390a8a9c3436706a05b63","source":{"kind":"arxiv","id":"2310.01688","version":1},"attestation_state":"computed","paper":{"title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jee-weon Jung, Samuele Cornell, Shinji Watanabe, Stefano Squartini","submitted_at":"2023-10-02T23:03:30Z","abstract_excerpt":"This paper presents a novel framework for joint speaker diarization (SD) and automatic speech recognition (ASR), named SLIDAR (sliding-window diarization-augmented recognition). SLIDAR can process arbitrary length inputs and can handle any number of speakers, effectively solving ``who spoke what, when'' concurrently. SLIDAR leverages a sliding window approach and consists of an end-to-end diarization-augmented speech transcription (E2E DAST) model which provides, locally, for each window: transcripts, diarization and speaker embeddings. The E2E DAST model is based on an encoder-decoder archite"},"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":"2310.01688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-02T23:03:30Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"4ae5013c3c5b417b533f39fb5d399f76bb9c98d2ec4bc5b8bacdbde4c6201c0d","abstract_canon_sha256":"a86521001a4c463deb93eeffc693215d30322f325aa3a4b7414ad247717252cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:44.849823Z","signature_b64":"p8sulc/P0HpP0picmUs0eyzx5KVPmsKdDo2IGllrbXZlLDcNmfrHc61Cdo3ONUYxHobVMkGi600EUmqnlDKNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f94fd953e7c33e06a6194a06846217c5187b92411d390a8a9c3436706a05b63","last_reissued_at":"2026-07-05T06:56:44.849363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:44.849363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jee-weon Jung, Samuele Cornell, Shinji Watanabe, Stefano Squartini","submitted_at":"2023-10-02T23:03:30Z","abstract_excerpt":"This paper presents a novel framework for joint speaker diarization (SD) and automatic speech recognition (ASR), named SLIDAR (sliding-window diarization-augmented recognition). SLIDAR can process arbitrary length inputs and can handle any number of speakers, effectively solving ``who spoke what, when'' concurrently. SLIDAR leverages a sliding window approach and consists of an end-to-end diarization-augmented speech transcription (E2E DAST) model which provides, locally, for each window: transcripts, diarization and speaker embeddings. The E2E DAST model is based on an encoder-decoder archite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01688","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/2310.01688/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":"2310.01688","created_at":"2026-07-05T06:56:44.849436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01688v1","created_at":"2026-07-05T06:56:44.849436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01688","created_at":"2026-07-05T06:56:44.849436+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6KP3FJ6PQZ6","created_at":"2026-07-05T06:56:44.849436+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6KP3FJ6PQZ6A2TB","created_at":"2026-07-05T06:56:44.849436+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6KP3FJ6","created_at":"2026-07-05T06:56:44.849436+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/H6KP3FJ6PQZ6A2TBSSQGQRRBPR","json":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR.json","graph_json":"https://pith.science/api/pith-number/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/graph.json","events_json":"https://pith.science/api/pith-number/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/events.json","paper":"https://pith.science/paper/H6KP3FJ6"},"agent_actions":{"view_html":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR","download_json":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR.json","view_paper":"https://pith.science/paper/H6KP3FJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01688&json=true","fetch_graph":"https://pith.science/api/pith-number/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/graph.json","fetch_events":"https://pith.science/api/pith-number/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/action/storage_attestation","attest_author":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/action/author_attestation","sign_citation":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/action/citation_signature","submit_replication":"https://pith.science/pith/H6KP3FJ6PQZ6A2TBSSQGQRRBPR/action/replication_record"}},"created_at":"2026-07-05T06:56:44.849436+00:00","updated_at":"2026-07-05T06:56:44.849436+00:00"}