{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HNJWOXGT2SL5MQLDHGALWLA62L","short_pith_number":"pith:HNJWOXGT","schema_version":"1.0","canonical_sha256":"3b53675cd3d497d641633980bb2c1ed2e193bc2e38eaa31b01ee5d1aa6e13daa","source":{"kind":"arxiv","id":"2011.02048","version":1},"attestation_state":"computed","paper":{"title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juan Pino, Philipp Koehn, Xutai Ma","submitted_at":"2020-11-03T22:47:58Z","abstract_excerpt":"Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging."},"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":"2011.02048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T22:47:58Z","cross_cats_sorted":[],"title_canon_sha256":"bd870babd42bed2ff16b833638d984cf1abe021d7d9bf82e16f7f6760ccf48dd","abstract_canon_sha256":"056c287ed8d61259333b871d292caa63dce005d2595319e4af9ddf786f581b48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:08.648249Z","signature_b64":"8cehOgajPDbZeFPNAjw1TEd4B8lEZyAw1SVYD7rn+xYx7BYosxifq05jjg9/ye7Xw4mDcwRHGmlXiOQ/L7d0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b53675cd3d497d641633980bb2c1ed2e193bc2e38eaa31b01ee5d1aa6e13daa","last_reissued_at":"2026-07-05T01:49:08.647862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:08.647862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juan Pino, Philipp Koehn, Xutai Ma","submitted_at":"2020-11-03T22:47:58Z","abstract_excerpt":"Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02048","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/2011.02048/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":"2011.02048","created_at":"2026-07-05T01:49:08.647923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02048v1","created_at":"2026-07-05T01:49:08.647923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02048","created_at":"2026-07-05T01:49:08.647923+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNJWOXGT2SL5","created_at":"2026-07-05T01:49:08.647923+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNJWOXGT2SL5MQLD","created_at":"2026-07-05T01:49:08.647923+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNJWOXGT","created_at":"2026-07-05T01:49:08.647923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07803","citing_title":"StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L","json":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L.json","graph_json":"https://pith.science/api/pith-number/HNJWOXGT2SL5MQLDHGALWLA62L/graph.json","events_json":"https://pith.science/api/pith-number/HNJWOXGT2SL5MQLDHGALWLA62L/events.json","paper":"https://pith.science/paper/HNJWOXGT"},"agent_actions":{"view_html":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L","download_json":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L.json","view_paper":"https://pith.science/paper/HNJWOXGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02048&json=true","fetch_graph":"https://pith.science/api/pith-number/HNJWOXGT2SL5MQLDHGALWLA62L/graph.json","fetch_events":"https://pith.science/api/pith-number/HNJWOXGT2SL5MQLDHGALWLA62L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L/action/storage_attestation","attest_author":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L/action/author_attestation","sign_citation":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L/action/citation_signature","submit_replication":"https://pith.science/pith/HNJWOXGT2SL5MQLDHGALWLA62L/action/replication_record"}},"created_at":"2026-07-05T01:49:08.647923+00:00","updated_at":"2026-07-05T01:49:08.647923+00:00"}