{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:57WD6E7YD7KARY76NDZOL77HU3","short_pith_number":"pith:57WD6E7Y","schema_version":"1.0","canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","source":{"kind":"arxiv","id":"2102.01757","version":2},"attestation_state":"computed","paper":{"title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Douglas W. Oard, Elizabeth Salesky, Jacob Bremerman, Marco Turchi, Matteo Negri, Matthew Wiesner, Matt Post, Roldano Cattoni","submitted_at":"2021-02-02T21:16:25Z","abstract_excerpt":"We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and speech translation (ST) research across many non-English source languages. The corpus is a collection of audio recordings from TEDx talks in 8 source languages. We segment transcripts into sentences and align them to the source-language audio and target-language translations. The corpus is released along with open-sourced code enabling extension to new talks and languages as they become available. Our corpus creation methodology can be applied to more languages than previous work, and creates multi-way paral"},"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":"2102.01757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"c8c1d18fec3cafae5577b84ecaf14cd4d1f9bc3967c5b5c0e6ab43d8f8f59418","abstract_canon_sha256":"317cd84525b2f2a4ca595c7813902a510093eec69b25218e5ddcc096ec7b65f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:24.482572Z","signature_b64":"AH1vyjatswh5+QXiXsN6fs0K8CzMp9YAoWsPutzT6hv5FKFArzx208FvrQA/44AAIc6Vj3n27KRQsQznkyjbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","last_reissued_at":"2026-07-05T02:49:24.482160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:24.482160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Douglas W. Oard, Elizabeth Salesky, Jacob Bremerman, Marco Turchi, Matteo Negri, Matthew Wiesner, Matt Post, Roldano Cattoni","submitted_at":"2021-02-02T21:16:25Z","abstract_excerpt":"We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and speech translation (ST) research across many non-English source languages. The corpus is a collection of audio recordings from TEDx talks in 8 source languages. We segment transcripts into sentences and align them to the source-language audio and target-language translations. The corpus is released along with open-sourced code enabling extension to new talks and languages as they become available. Our corpus creation methodology can be applied to more languages than previous work, and creates multi-way paral"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01757","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/2102.01757/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":"2102.01757","created_at":"2026-07-05T02:49:24.482219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.01757v2","created_at":"2026-07-05T02:49:24.482219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01757","created_at":"2026-07-05T02:49:24.482219+00:00"},{"alias_kind":"pith_short_12","alias_value":"57WD6E7YD7KA","created_at":"2026-07-05T02:49:24.482219+00:00"},{"alias_kind":"pith_short_16","alias_value":"57WD6E7YD7KARY76","created_at":"2026-07-05T02:49:24.482219+00:00"},{"alias_kind":"pith_short_8","alias_value":"57WD6E7Y","created_at":"2026-07-05T02:49:24.482219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13121","citing_title":"NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3","json":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3.json","graph_json":"https://pith.science/api/pith-number/57WD6E7YD7KARY76NDZOL77HU3/graph.json","events_json":"https://pith.science/api/pith-number/57WD6E7YD7KARY76NDZOL77HU3/events.json","paper":"https://pith.science/paper/57WD6E7Y"},"agent_actions":{"view_html":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3","download_json":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3.json","view_paper":"https://pith.science/paper/57WD6E7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.01757&json=true","fetch_graph":"https://pith.science/api/pith-number/57WD6E7YD7KARY76NDZOL77HU3/graph.json","fetch_events":"https://pith.science/api/pith-number/57WD6E7YD7KARY76NDZOL77HU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/action/storage_attestation","attest_author":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/action/author_attestation","sign_citation":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/action/citation_signature","submit_replication":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/action/replication_record"}},"created_at":"2026-07-05T02:49:24.482219+00:00","updated_at":"2026-07-05T02:49:24.482219+00:00"}