{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LG2UWFFSIO2ODVALDENI23J3UK","short_pith_number":"pith:LG2UWFFS","schema_version":"1.0","canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","source":{"kind":"arxiv","id":"2404.11619","version":1},"attestation_state":"computed","paper":{"title":"Advancing Speech Translation: A Corpus of Mandarin-English Conversational Telephone Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Matthew Snover, Shannon Wotherspoon, William Hartmann","submitted_at":"2024-03-25T21:08:06Z","abstract_excerpt":"This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and target-language text is essential for training end-to-end speech translation systems and can provide substantial performance improvements for cascaded systems as well, relative to training on more widely available text data sets. We demonstrate that fine-tuning a general-purpose translation model to our Mandarin-English conversational telephone speech training set improv"},"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":"2404.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"66fab5f5532059e70fc33c86d7ebcf7d35f37ee4301ed3d8226fe764cf9e8100","abstract_canon_sha256":"9bd95b660e7d021f4cb80cc725329209d275bac61dbe36a5ab86a397b1ef8a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:13.672812Z","signature_b64":"50gx7ni44J0yTEVSRlEg4P4e3tjYKf2zhxCMjXVebBvsqutwA2Olv/cKPvpj7u8bqBptkjLiE9BIcDNNhxc0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","last_reissued_at":"2026-07-05T08:09:13.672390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:13.672390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Speech Translation: A Corpus of Mandarin-English Conversational Telephone Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Matthew Snover, Shannon Wotherspoon, William Hartmann","submitted_at":"2024-03-25T21:08:06Z","abstract_excerpt":"This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and target-language text is essential for training end-to-end speech translation systems and can provide substantial performance improvements for cascaded systems as well, relative to training on more widely available text data sets. We demonstrate that fine-tuning a general-purpose translation model to our Mandarin-English conversational telephone speech training set improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11619","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/2404.11619/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":"2404.11619","created_at":"2026-07-05T08:09:13.672449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11619v1","created_at":"2026-07-05T08:09:13.672449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11619","created_at":"2026-07-05T08:09:13.672449+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG2UWFFSIO2O","created_at":"2026-07-05T08:09:13.672449+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG2UWFFSIO2ODVAL","created_at":"2026-07-05T08:09:13.672449+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG2UWFFS","created_at":"2026-07-05T08:09:13.672449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02157","citing_title":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK","json":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK.json","graph_json":"https://pith.science/api/pith-number/LG2UWFFSIO2ODVALDENI23J3UK/graph.json","events_json":"https://pith.science/api/pith-number/LG2UWFFSIO2ODVALDENI23J3UK/events.json","paper":"https://pith.science/paper/LG2UWFFS"},"agent_actions":{"view_html":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK","download_json":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK.json","view_paper":"https://pith.science/paper/LG2UWFFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11619&json=true","fetch_graph":"https://pith.science/api/pith-number/LG2UWFFSIO2ODVALDENI23J3UK/graph.json","fetch_events":"https://pith.science/api/pith-number/LG2UWFFSIO2ODVALDENI23J3UK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/action/storage_attestation","attest_author":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/action/author_attestation","sign_citation":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/action/citation_signature","submit_replication":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/action/replication_record"}},"created_at":"2026-07-05T08:09:13.672449+00:00","updated_at":"2026-07-05T08:09:13.672449+00:00"}