{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IXJ6HLLEQSW7CW6XWMSC5BGSLU","short_pith_number":"pith:IXJ6HLLE","schema_version":"1.0","canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","source":{"kind":"arxiv","id":"2309.15013","version":1},"attestation_state":"computed","paper":{"title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Corey Miller, Desh Raj, Jennifer Drexler Fox, Mig\\\"uel Jett\\'e, Natalie Delworth, Quinn McNamara","submitted_at":"2023-09-26T15:32:09Z","abstract_excerpt":"The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between inference-time conditions and models trained on segmented utterances. In this paper, we re-release three standard ASR corpora - TED-LIUM 3, Gigapeech, and VoxPopuli-en - with updated transcription and alignments to enable their use for long-form ASR research. We use these reconstituted corpora to study the train-test mismatch problem for transducers and attention-base"},"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":"2309.15013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c38f79cc31971b7c397309310316838d3f268db911558e41891e45d5463660de","abstract_canon_sha256":"5e4784eac8a900b156b1d57d14d056150e23735ee7adef45615390c9b5f17f85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:32.754329Z","signature_b64":"RBFS52bpOCwTBJ3Hcqg/fqcs3A9gwqSo0JNCl3v8+gKSU9HrxqSLkGEHcejE2B/hdyoLVVEswlGX3vSVVSC+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","last_reissued_at":"2026-07-05T06:54:32.753823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:32.753823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Corey Miller, Desh Raj, Jennifer Drexler Fox, Mig\\\"uel Jett\\'e, Natalie Delworth, Quinn McNamara","submitted_at":"2023-09-26T15:32:09Z","abstract_excerpt":"The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between inference-time conditions and models trained on segmented utterances. In this paper, we re-release three standard ASR corpora - TED-LIUM 3, Gigapeech, and VoxPopuli-en - with updated transcription and alignments to enable their use for long-form ASR research. We use these reconstituted corpora to study the train-test mismatch problem for transducers and attention-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15013","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/2309.15013/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":"2309.15013","created_at":"2026-07-05T06:54:32.753882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15013v1","created_at":"2026-07-05T06:54:32.753882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15013","created_at":"2026-07-05T06:54:32.753882+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXJ6HLLEQSW7","created_at":"2026-07-05T06:54:32.753882+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXJ6HLLEQSW7CW6X","created_at":"2026-07-05T06:54:32.753882+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXJ6HLLE","created_at":"2026-07-05T06:54:32.753882+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/IXJ6HLLEQSW7CW6XWMSC5BGSLU","json":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU.json","graph_json":"https://pith.science/api/pith-number/IXJ6HLLEQSW7CW6XWMSC5BGSLU/graph.json","events_json":"https://pith.science/api/pith-number/IXJ6HLLEQSW7CW6XWMSC5BGSLU/events.json","paper":"https://pith.science/paper/IXJ6HLLE"},"agent_actions":{"view_html":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU","download_json":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU.json","view_paper":"https://pith.science/paper/IXJ6HLLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15013&json=true","fetch_graph":"https://pith.science/api/pith-number/IXJ6HLLEQSW7CW6XWMSC5BGSLU/graph.json","fetch_events":"https://pith.science/api/pith-number/IXJ6HLLEQSW7CW6XWMSC5BGSLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/action/storage_attestation","attest_author":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/action/author_attestation","sign_citation":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/action/citation_signature","submit_replication":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/action/replication_record"}},"created_at":"2026-07-05T06:54:32.753882+00:00","updated_at":"2026-07-05T06:54:32.753882+00:00"}