{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RRWLGGS6S3WX7QATQSON2IS6YG","short_pith_number":"pith:RRWLGGS6","schema_version":"1.0","canonical_sha256":"8c6cb31a5e96ed7fc013849cdd225ec19717f7eba368d742b845b776184c820d","source":{"kind":"arxiv","id":"2203.14835","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Simultaneous Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jan Niehues, Shashank Subramanya","submitted_at":"2022-03-28T15:17:11Z","abstract_excerpt":"Applications designed for simultaneous speech translation during events such as conferences or meetings need to balance quality and lag while displaying translated text to deliver a good user experience. One common approach to building online spoken language translation systems is by leveraging models built for offline speech translation. Based on a technique to adapt end-to-end monolingual models, we investigate multilingual models and different architectures (end-to-end and cascade) on the ability to perform online speech translation. On the multilingual TEDx corpus, we show that the approac"},"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":"2203.14835","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-28T15:17:11Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c27df187597d28eb8e8aa5969adbfa1f91ff5c6a65799a0bcc013de735cb6665","abstract_canon_sha256":"29a6b809bc58dc6fecb727bf2974b7d763a861e6227aae04ae05a66dc7576fb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:20.406172Z","signature_b64":"SkNrJ56NznHuAm0PVRdGj3YbfRcz/R17Njy3Cq+gnfOKVKTeF1Lw5Abmh5gc8m4LXCk1NWHMrhWFds9rMIgOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6cb31a5e96ed7fc013849cdd225ec19717f7eba368d742b845b776184c820d","last_reissued_at":"2026-07-05T04:09:20.405705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:20.405705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Simultaneous Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jan Niehues, Shashank Subramanya","submitted_at":"2022-03-28T15:17:11Z","abstract_excerpt":"Applications designed for simultaneous speech translation during events such as conferences or meetings need to balance quality and lag while displaying translated text to deliver a good user experience. One common approach to building online spoken language translation systems is by leveraging models built for offline speech translation. Based on a technique to adapt end-to-end monolingual models, we investigate multilingual models and different architectures (end-to-end and cascade) on the ability to perform online speech translation. On the multilingual TEDx corpus, we show that the approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14835","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/2203.14835/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":"2203.14835","created_at":"2026-07-05T04:09:20.405766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14835v2","created_at":"2026-07-05T04:09:20.405766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14835","created_at":"2026-07-05T04:09:20.405766+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRWLGGS6S3WX","created_at":"2026-07-05T04:09:20.405766+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRWLGGS6S3WX7QAT","created_at":"2026-07-05T04:09:20.405766+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRWLGGS6","created_at":"2026-07-05T04:09:20.405766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18495","citing_title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG","json":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG.json","graph_json":"https://pith.science/api/pith-number/RRWLGGS6S3WX7QATQSON2IS6YG/graph.json","events_json":"https://pith.science/api/pith-number/RRWLGGS6S3WX7QATQSON2IS6YG/events.json","paper":"https://pith.science/paper/RRWLGGS6"},"agent_actions":{"view_html":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG","download_json":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG.json","view_paper":"https://pith.science/paper/RRWLGGS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14835&json=true","fetch_graph":"https://pith.science/api/pith-number/RRWLGGS6S3WX7QATQSON2IS6YG/graph.json","fetch_events":"https://pith.science/api/pith-number/RRWLGGS6S3WX7QATQSON2IS6YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG/action/storage_attestation","attest_author":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG/action/author_attestation","sign_citation":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG/action/citation_signature","submit_replication":"https://pith.science/pith/RRWLGGS6S3WX7QATQSON2IS6YG/action/replication_record"}},"created_at":"2026-07-05T04:09:20.405766+00:00","updated_at":"2026-07-05T04:09:20.405766+00:00"}