{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WQLTBFCOKT2RBC36WDBVKV2ZZY","short_pith_number":"pith:WQLTBFCO","schema_version":"1.0","canonical_sha256":"b41730944e54f5108b7eb0c3555759ce25bb71cb94060104bcc53f7bc57b9e11","source":{"kind":"arxiv","id":"2210.07771","version":1},"attestation_state":"computed","paper":{"title":"Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet","submitted_at":"2022-10-14T13:01:00Z","abstract_excerpt":"TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two "},"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":"2210.07771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-14T13:01:00Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"46a477978b980a5027b67b8672843ab245fb8e2fdc3e73977f251a18fe9db3cd","abstract_canon_sha256":"ad8c6a39a5dce8ddd2c3423df5bbfc2e6d56b0f728caeec3334fda8d3c4144ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:40.931948Z","signature_b64":"L1yCAzSHV7fsbSBCJruhH8/0vKypdGFJVW9j5LNjL6Jsm6+C7z6jC+FsosTUi2vvPCTkCRg8vFImxoajz1ixCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b41730944e54f5108b7eb0c3555759ce25bb71cb94060104bcc53f7bc57b9e11","last_reissued_at":"2026-07-05T05:06:40.931424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:40.931424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet","submitted_at":"2022-10-14T13:01:00Z","abstract_excerpt":"TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07771","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/2210.07771/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":"2210.07771","created_at":"2026-07-05T05:06:40.931484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07771v1","created_at":"2026-07-05T05:06:40.931484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07771","created_at":"2026-07-05T05:06:40.931484+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQLTBFCOKT2R","created_at":"2026-07-05T05:06:40.931484+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQLTBFCOKT2RBC36","created_at":"2026-07-05T05:06:40.931484+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQLTBFCO","created_at":"2026-07-05T05:06:40.931484+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/WQLTBFCOKT2RBC36WDBVKV2ZZY","json":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY.json","graph_json":"https://pith.science/api/pith-number/WQLTBFCOKT2RBC36WDBVKV2ZZY/graph.json","events_json":"https://pith.science/api/pith-number/WQLTBFCOKT2RBC36WDBVKV2ZZY/events.json","paper":"https://pith.science/paper/WQLTBFCO"},"agent_actions":{"view_html":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY","download_json":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY.json","view_paper":"https://pith.science/paper/WQLTBFCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07771&json=true","fetch_graph":"https://pith.science/api/pith-number/WQLTBFCOKT2RBC36WDBVKV2ZZY/graph.json","fetch_events":"https://pith.science/api/pith-number/WQLTBFCOKT2RBC36WDBVKV2ZZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY/action/storage_attestation","attest_author":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY/action/author_attestation","sign_citation":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY/action/citation_signature","submit_replication":"https://pith.science/pith/WQLTBFCOKT2RBC36WDBVKV2ZZY/action/replication_record"}},"created_at":"2026-07-05T05:06:40.931484+00:00","updated_at":"2026-07-05T05:06:40.931484+00:00"}